INDEX

Explanations

phrases related to tolerating or enduring something unpleasant

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of "putting up" or tolerance

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

=]

-0.77

jong

-0.66

gee

-0.65

 certific

-0.63

 Austral

-0.62

igue

-0.62

 CLSID

-0.61

 gearing

-0.60

JA

-0.59

 vers

-0.58

POSITIVE LOGITS

ris

0.89

rights

0.73

 banners

0.71

river

0.71

earance

0.71

 posters

0.70

rescent

0.69

 fences

0.69

 tents

0.68

amina

0.68

Activations Density 0.030%

phrases related to tolerating or enduring something unpleasant

phrases related to the concept of "putting up" or tolerance

No Comments

No Known Activations