INDEX

Explanations

words or parts of words containing "ew"

oai_token-act-pair · gpt-3.5-turbo

the word "new"

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

 cort

-0.71

 retri

-0.67

Downloadha

-0.66

 burg

-0.65

 unarmed

-0.63

 apprehend

-0.63

 thieves

-0.63

REDACTED

-0.62

 administr

-0.61

esthetic

-0.61

POSITIVE LOGITS

estern

1.24

atts

0.99

esley

0.98

ew

0.97

een

0.96

sburg

0.95

olf

0.93

ild

0.92

eeks

0.92

ITNESS

0.91

Activations Density 0.009%

words or parts of words containing "ew"

the word "new"

No Comments

No Known Activations