INDEX

Explanations

references to units of measurement

oai_token-act-pair · gpt-3.5-turbo

references to personal pronouns and familial relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Accountability

-0.74

selves

-0.63

 Provision

-0.60

USA

-0.60

 meanwhile

-0.60

 overnight

-0.59

 Finance

-0.59

terday

-0.59

 Quote

-0.57

 Cost

-0.56

POSITIVE LOGITS

alian

0.95

pher

0.88

andering

0.85

aned

0.84

oxic

0.84

kan

0.83

avering

0.83

athy

0.83

aded

0.82

adow

0.82

Activations Density 0.154%

references to units of measurement

references to personal pronouns and familial relationships

No Comments

No Known Activations