INDEX

Explanations

words related to a specific location, "Guwahati"

oai_token-act-pair · gpt-3.5-turbo

the character 'w' in a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

uate

-0.82

 paraly

-0.74

staking

-0.68

âĸ¬

-0.68

uated

-0.65

 conscientious

-0.63

REDACTED

-0.61

 suspic

-0.60

 mosqu

-0.59

 foss

-0.59

POSITIVE LOGITS

elcome

1.24

atts

1.20

itness

1.19

isdom

1.17

ashington

1.15

izard

1.14

atcher

1.13

atson

1.12

isconsin

1.09

restling

1.07

Activations Density 0.048%

words related to a specific location, "Guwahati"

the character 'w' in a variety of contexts

No Comments

No Known Activations