INDEX

Explanations

words related to the concept of inclusion and exclusion

oai_token-act-pair · gpt-3.5-turbo

concepts related to social inclusion and exclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 decl

-0.72

 weap

-0.64

ieri

-0.63

acca

-0.62

 physic

-0.62

rpm

-0.61

ELL

-0.61

 Indust

-0.60

 bath

-0.59

 Federation

-0.56

POSITIVE LOGITS

ary

1.08

ibility

0.87

naire

0.85

clusion

0.84

tions

0.80

iveness

0.79

 criteria

0.77

aries

0.77

ism

0.77

liga

0.76

Activations Density 0.043%

words related to the concept of inclusion and exclusion

concepts related to social inclusion and exclusion

No Comments

No Known Activations