INDEX

Explanations

verbs expressing actions or comparisons

oai_token-act-pair · gpt-3.5-turbo

phrases that describe analogies or comparisons involving actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ersen

-0.71

ses

-0.63

ifer

-0.62

 barring

-0.62

avage

-0.61

Ã¨re

-0.60

 showing

-0.59

OUND

-0.59

lease

-0.59

 ending

-0.58

POSITIVE LOGITS

 oneself

1.22

 Yourself

0.93

 yourself

0.82

 Pengu

0.69

 strangers

0.66

 toget

0.65

 immersed

0.64

ocial

0.62

ãĥ³ãĤ¸

0.61

omorphic

0.61

Activations Density 0.362%

verbs expressing actions or comparisons

phrases that describe analogies or comparisons involving actions

No Comments

No Known Activations