INDEX

Explanations

phrases indicating assistance, support, or benefits

oai_token-act-pair · gpt-3.5-turbo

references to assistance or support

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

theless

-0.75

 scanned

-0.73

æ³

-0.67

ata

-0.65

aults

-0.63

 TABLE

-0.59

ulations

-0.58

tains

-0.58

avior

-0.57

wear

-0.57

POSITIVE LOGITS

 alleviate

0.89

 lessen

0.81

 relieve

0.80

 disguise

0.79

fully

0.79

 stabilize

0.79

 morale

0.78

 strengthen

0.78

 tremendously

0.77

 ease

0.76

Activations Density 0.065%

phrases indicating assistance, support, or benefits

references to assistance or support

No Comments

No Known Activations