INDEX

Explanations

words related to individuals or places with the syllable "an"

oai_token-act-pair · gpt-3.5-turbo

the word "an" 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 @ 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

ï¸ı

-0.94

hovah

-0.87

atility

-0.78

 WATCHED

-0.76

 guiIcon

-0.75

uably

-0.72

ensional

-0.71

IBLE

-0.71

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.71

 ACTIONS

-0.70

POSITIVE LOGITS

igans

1.33

xiety

1.06

thus

1.05

alyst

1.03

ghai

1.02

ning

1.02

onymous

1.00

esthetic

0.98

ufact

0.96

odon

0.94

Activations Density 0.049%

words related to individuals or places with the syllable "an"

the word "an" in various contexts

No Comments

No Known Activations