INDEX

Explanations

words related to evidence or proof

oai_token-act-pair · gpt-3.5-turbo

words that indicate proof, evidence, or signs of certain claims or conditions

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

onyms

-0.73

tones

-0.72

 throats

-0.70

otin

-0.66

ophon

-0.63

 diction

-0.63

enz

-0.62

atomic

-0.61

hari

-0.61

atography

-0.60

POSITIVE LOGITS

baugh

0.72

 thereof

0.72

rance

0.71

 reminder

0.70

 emblem

0.70

ially

0.69

bringer

0.68

uer

0.68

NUM

0.67

alled

0.67

Activations Density 0.100%

words related to evidence or proof

words that indicate proof, evidence, or signs of certain claims or conditions

No Comments

No Known Activations