INDEX

Explanations

medical and scientific terms or technical jargon

oai_token-act-pair · gpt-3.5-turbo

the presence of end-of-text markers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

avorite

-0.76

 scrut

-0.72

 predec

-0.70

 Jagu

-0.69

Repeat

-0.68

ãĥ¯ãĥ³

-0.68

accompan

-0.67

[*

-0.67

 destro

-0.64

 undermin

-0.63

POSITIVE LOGITS

 Profile

0.80

fi

0.69

photos

0.67

sonian

0.66

nee

0.66

hi

0.64

ci

0.64

hu

0.63

eat

0.62

ho

0.60

Activations Density 0.340%

medical and scientific terms or technical jargon

the presence of end-of-text markers

No Comments

No Known Activations