INDEX

Explanations

adjectives indicating positive evaluation or appreciation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "pretty" used to express moderate approval or positivity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

venant

-0.79

 ILCS

-0.72

KY

-0.72

FTA

-0.72

upon

-0.71

 Flavoring

-0.70

pent

-0.69

arta

-0.69

RY

-0.68

ortmund

-0.66

POSITIVE LOGITS

 darn

1.23

 nifty

1.02

 neat

0.96

 much

0.95

 awesome

0.92

 straightforward

0.92

 scary

0.91

 damn

0.90

 interesting

0.90

 snipp

0.88

Activations Density 0.032%

adjectives indicating positive evaluation or appreciation

instances of the word "pretty" used to express moderate approval or positivity

No Comments

No Known Activations