INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

specific names or acronyms related to organizations, entities, or groups

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

terday

-0.79

abwe

-0.70

 âĢº

-0.69

 ..........

-0.68

Ú

-0.67

conserv

-0.64

Ô

-0.64

ctica

-0.62

ÙĦ

-0.61

ãģ«

-0.61

POSITIVE LOGITS

ultimate

0.80

iest

0.72

 Gazette

0.71

 Nebula

0.70

agame

0.70

 logo

0.69

hest

0.68

 ecosystem

0.67

verse

0.67

osphere

0.67

Activations Density 0.368%

proper nouns or names

specific names or acronyms related to organizations, entities, or groups

No Comments

No Known Activations