INDEX

Explanations

phrases related to specific locations or organizations

oai_token-act-pair · gpt-3.5-turbo

references to intelligence agencies, military locations, and various government entities or regions

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

ynt

-0.71

iors

-0.71

called

-0.66

 dolphins

-0.66

pedia

-0.62

angible

-0.61

\/\/

-0.61

ueless

-0.60

Mer

-0.59

Anonymous

-0.58

POSITIVE LOGITS

ridor

0.71

insula

0.68

eele

0.67

arette

0.65

hyde

0.65

ricular

0.65

 Railway

0.65

 Treaty

0.65

rity

0.63

cius

0.62

Activations Density 0.108%

phrases related to specific locations or organizations

references to intelligence agencies, military locations, and various government entities or regions

No Comments

No Known Activations