INDEX

Explanations

references to news articles or stories

oai_token-act-pair · gpt-3.5-turbo

mentions of news sources or news-related content

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

phrine

-0.74

Â¯Â¯

-0.70

ength

-0.70

inished

-0.69

Äĩ

-0.67

qqa

-0.67

hetti

-0.67

 downs

-0.66

llular

-0.66

staking

-0.66

POSITIVE LOGITS

letters

1.08

room

0.97

ource

0.93

letter

0.88

reader

0.87

 Tycoon

0.83

 Coverage

0.82

 Releases

0.82

feed

0.81

orial

0.81

Activations Density 0.032%

references to news articles or stories

mentions of news sources or news-related content

No Comments

No Known Activations