INDEX

Explanations

references to Frequently Asked Questions (FAQs)

oai_token-act-pair · gpt-3.5-turbo

references to FAQs and related help resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

arnaev

-0.84

heimer

-0.73

akin

-0.71

kus

-0.71

rigan

-0.69

ographed

-0.69

Eye

-0.69

intent

-0.68

agers

-0.68

red

-0.68

POSITIVE LOGITS

FAQ

0.88

sie

0.88

 Questions

0.82

naires

0.73

 Answer

0.73

 homepage

0.72

sers

0.71

 answered

0.69

FAQ

0.69

 Answers

0.68

Activations Density 0.017%

references to Frequently Asked Questions (FAQs)

references to FAQs and related help resources

No Comments

No Known Activations