INDEX

Explanations

references to a specific word or name 'row'

oai_token-act-pair · gpt-3.5-turbo

sequences of words that include variations of the word "row."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

£ı

-0.78

 flaw

-0.73

ãĥ¤

-0.72

 metic

-0.71

ĺħ

-0.70

urated

-0.69

 mosqu

-0.66

 authentic

-0.65

 fragmented

-0.65

CoC

-0.65

POSITIVE LOGITS

row

1.33

restling

1.02

icz

0.96

rows

0.92

ars

0.89

dy

0.86

ski

0.85

lings

0.84

TPPStreamerBot

0.83

feed

0.82

Activations Density 0.006%

references to a specific word or name 'row'

sequences of words that include variations of the word "row."

No Comments

No Known Activations