INDEX

Explanations

specific technical terms related to various industries or fields such as technology, healthcare, and entertainment

oai_token-act-pair · gpt-3.5-turbo

specific brands, products, or entities mentioned in a technical or business context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 horizont

-0.57

è¦ļéĨĴ

-0.56

 sidx

-0.55

utenberg

-0.55

 tremend

-0.54

ccording

-0.54

inarily

-0.53

ependent

-0.53

 reconc

-0.53

 silence

-0.52

POSITIVE LOGITS

ensis

0.67

eus

0.67

naire

0.55

orum

0.55

Jr

0.54

gmail

0.53

egu

0.52

âĢİ

0.51

fo

0.51

reck

0.50

Activations Density 1.049%

specific technical terms related to various industries or fields such as technology, healthcare, and entertainment

specific brands, products, or entities mentioned in a technical or business context

No Comments

No Known Activations