INDEX

Explanations

words and phrases indicating positive or negative evaluation

oai_token-act-pair · gpt-3.5-turbo

phrases that evaluate actions or circumstances as either good or bad

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

 largeDownload

-0.72

uum

-0.71

oufl

-0.71

geons

-0.70

zing

-0.67

ardless

-0.66

uates

-0.65

ensitive

-0.65

othal

-0.63

ADRA

-0.63

POSITIVE LOGITS

 happened

1.01

 happening

0.95

 happen

0.92

 happens

0.84

 happ

0.77

Else

0.76

 imaginable

0.74

iverse

0.71

 Happ

0.71

 Done

0.66

Activations Density 0.045%

words and phrases indicating positive or negative evaluation

phrases that evaluate actions or circumstances as either good or bad

No Comments

No Known Activations