INDEX

Explanations

mentions or instances of the word "proof" in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "proof" and its variations, indicating a focus on verification or evidence

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 livest

-0.79

artney

-0.69

Osc

-0.69

ideshow

-0.68

lished

-0.68

ufact

-0.67

 Peninsula

-0.66

asions

-0.66

iewicz

-0.66

 contrace

-0.65

POSITIVE LOGITS

reading

1.23

reader

1.07

read

0.95

edly

0.94

ificate

0.88

 proof

0.85

ing

0.85

ingen

0.83

 proofs

0.82

uers

0.81

Activations Density 0.016%

mentions or instances of the word "proof" in various contexts

instances of the word "proof" and its variations, indicating a focus on verification or evidence

No Comments

No Known Activations