INDEX

Explanations

proper nouns, likely names and locations

oai_token-act-pair · gpt-3.5-turbo

references to the term "Dj" and its various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

rawdownloadcloneembedreportprint

-0.91

Interstitial

-0.75

child

-0.74

WORK

-0.71

izations

-0.70

nings

-0.69

 Collider

-0.69

RIS

-0.67

 Huntington

-0.67

 contraception

-0.64

POSITIVE LOGITS

Dj

1.11

itsu

0.93

uda

0.88

inn

0.86

itto

0.86

Ã¶r

0.85

tch

0.82

arl

0.81

erm

0.81

uran

0.80

Activations Density 0.007%

proper nouns, likely names and locations

references to the term "Dj" and its various contexts

No Comments

No Known Activations