INDEX

Explanations

proper nouns specifically indicated by the article "a" or "an"

oai_token-act-pair · gpt-3.5-turbo

articles and quantifiers in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

oper

-0.78

ilty

-0.75

eye

-0.75

eno

-0.74

imar

-0.73

anism

-0.71

apo

-0.70

alties

-0.69

apest

-0.68

Own

-0.68

POSITIVE LOGITS

 mysterious

0.86

 flurry

0.85

 spate

0.85

 bombshell

0.84

 consortium

0.82

 group

0.80

 masked

0.79

 unidentified

0.78

 slew

0.77

 coalition

0.77

Activations Density 0.220%

proper nouns specifically indicated by the article "a" or "an"

articles and quantifiers in a text

No Comments

No Known Activations