INDEX

Explanations

ill-formed words

oai_token-act-pair · gpt-3.5-turbo

words related to slurs or derogatory terms

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

ICLE

-0.78

ãģ®éŃĶ

-0.76

IFIC

-0.74

enegger

-0.73

 Cause

-0.68

éļ

-0.65

BLIC

-0.65

 Realms

-0.64

Trust

-0.63

terms

-0.63

POSITIVE LOGITS

anted

1.19

udge

1.16

ugg

1.16

otted

1.14

ights

1.13

asher

1.12

ashes

1.12

ither

1.12

inging

1.11

ipp

1.11

Activations Density 0.010%

ill-formed words

words related to slurs or derogatory terms

No Comments

No Known Activations