INDEX

Explanations

the word "ome"

oai_token-act-pair · gpt-3.5-turbo

the word "some."

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

taboola

-0.71

ulates

-0.70

lished

-0.70

iversal

-0.68

Reviewer

-0.66

icter

-0.65

ungle

-0.65

olicy

-0.64

hops

-0.63

atever

-0.62

POSITIVE LOGITS

ome

1.45

lement

0.94

ppa

0.84

OME

0.82

lette

0.79

 Parenthood

0.77

 Pengu

0.74

omic

0.73

erous

0.73

anic

0.71

Activations Density 0.007%

the word "ome"

the word "some."

No Comments

No Known Activations