INDEX

Explanations

words related to improvements or enhancements

oai_token-act-pair · gpt-3.5-turbo

references to enhancements or betterments in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itto

-0.73

ãĥĥãĥī

-0.70

thur

-0.70

leton

-0.68

cium

-0.67

ptin

-0.64

regate

-0.63

azine

-0.63

rake

-0.61

andra

-0.61

POSITIVE LOGITS

ments

0.88

 improvement

0.78

ment

0.76

 enhancement

0.73

 agre

0.71

xual

0.69

 improvements

0.69

 attainment

0.69

iants

0.68

Score

0.68

Activations Density 0.028%

words related to improvements or enhancements

references to enhancements or betterments in various contexts

No Comments

No Known Activations