INDEX

Explanations

phrases related to various specific communities or groups

oai_token-act-pair · gpt-3.5-turbo

the word "in" and its frequency within context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

enza

-0.72

Completed

-0.64

0000000000000000

-0.63

rifice

-0.62

:/

-0.61

ograms

-0.61

dule

-0.60

iris

-0.60

discrimination

-0.57

iour

-0.57

POSITIVE LOGITS

 academia

1.35

 Silicon

1.02

 circles

0.98

 Congress

0.97

 fandom

0.94

 Europe

0.93

 Washington

0.93

roads

0.85

 forums

0.83

 mainstream

0.83

Activations Density 0.191%

phrases related to various specific communities or groups

the word "in" and its frequency within context

No Comments

No Known Activations