INDEX

Explanations

links to further information within text

oai_token-act-pair · gpt-3.5-turbo

phrases that encourage reading and exploring additional information

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

ENTION

-0.68

oses

-0.67

endant

-0.67

pires

-0.67

aired

-0.65

oppy

-0.65

ĸļ

-0.65

osing

-0.64

icans

-0.63

Ħ¢

-0.63

POSITIVE LOGITS

 snipp

0.81

 HERE

0.79

 yourself

0.77

SOURCE

0.76

pdf

0.72

 subscript

0.71

 yourselves

0.70

 Attribution

0.70

 download

0.69

PDF

0.68

Activations Density 0.097%

links to further information within text

phrases that encourage reading and exploring additional information

No Comments

No Known Activations