INDEX

Explanations

phrases related to inclusivity and effectiveness

oai_token-act-pair · gpt-3.5-turbo

words related to inclusivity and its impact

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

accompan

-0.74

ŃĶ

-0.71

Dri

-0.60

Ct

-0.59

zb

-0.59

pid

-0.59

TG

-0.57

Austin

-0.56

points

-0.55

Ü

-0.55

POSITIVE LOGITS

ividual

0.82

uments

0.73

urities

0.71

uration

0.70

uable

0.69

ibles

0.64

ision

0.64

ãĤ¨ãĥ«

0.63

querque

0.63

itably

0.62

Activations Density 0.037%

phrases related to inclusivity and effectiveness

words related to inclusivity and its impact

No Comments

No Known Activations