INDEX

Explanations

specific years mentioned in the documents

oai_token-act-pair · gpt-3.5-turbo

references to parentheses in film or documentary titles, years, and notable names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ahu

-0.79

rew

-0.73

 crate

-0.68

itory

-0.66

heard

-0.65

azon

-0.65

 administrator

-0.65

unia

-0.65

onite

-0.64

ĵĺ

-0.63

POSITIVE LOGITS

 onwards

0.87

 Surviv

0.72

 Anniversary

0.66

 Chiefs

0.65

 RELE

0.65

 Reincarn

0.63

ESV

0.61

CRC

0.61

 Lawyers

0.61

 Frames

0.60

Activations Density 0.105%

specific years mentioned in the documents

references to parentheses in film or documentary titles, years, and notable names

No Comments

No Known Activations