INDEX

Explanations

mentions of specific nouns preceded by "the."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Supported

-0.86

thood

-0.82

ca

-0.81

icia

-0.81

cation

-0.78

tesy

-0.76

auri

-0.75

ACY

-0.74

dding

-0.73

ipping

-0.72

POSITIVE LOGITS

 slightest

1.02

 heck

0.93

 vast

0.91

 curtain

0.83

 disparate

0.83

ses

0.82

 entire

0.82

 world

0.78

 greatest

0.78

 hell

0.78

Activations Density 0.217%

mentions of specific nouns preceded by "the."

occurrences of the word "the."

No Comments

No Known Activations