INDEX

Explanations

the word "Proof"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "proof" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ideshow

-0.72

 livest

-0.70

 Peninsula

-0.65

ktop

-0.64

 contrace

-0.63

artney

-0.63

phrine

-0.63

asions

-0.62

Osc

-0.62

avy

-0.61

POSITIVE LOGITS

reading

1.16

reader

1.00

 proof

0.96

read

0.93

edly

0.89

 proofs

0.88

ificate

0.87

proof

0.87

Proof

0.79

ingen

0.76

Activations Density 0.023%

the word "Proof"

instances of the word "proof" in various contexts

No Comments

No Known Activations