INDEX

Explanations

phrases related to disparities and differences

oai_token-act-pair · gpt-3.5-turbo

references to disparities or differences, particularly those labeled as "gaps."

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

der

-0.68

rich

-0.68

di

-0.65

ivery

-0.64

vez

-0.63

ise

-0.60

vic

-0.59

gg

-0.59

ocations

-0.58

asting

-0.57

POSITIVE LOGITS

 between

1.10

between

1.03

wid

1.03

gap

0.95

 widened

0.94

 widen

0.88

 Between

0.88

 separating

0.86

 widening

0.80

Gap

0.79

Activations Density 0.046%

phrases related to disparities and differences

references to disparities or differences, particularly those labeled as "gaps."

No Comments

No Known Activations