INDEX

Explanations

numerical ratings or evaluations given to various entities

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate ratings or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

vous

-0.92

Nou

-0.82

ansson

-0.77

vas

-0.76

adr

-0.75

alter

-0.75

olding

-0.73

nee

-0.72

isting

-0.72

Alz

-0.71

POSITIVE LOGITS

 rated

1.38

 veter

1.05

 ratings

1.04

 rating

1.04

 unbeliev

0.99

 Ratings

0.96

Rated

0.95

 Rated

0.91

 conflic

0.91

 millenn

0.89

Activations Density 0.007%

numerical ratings or evaluations given to various entities

phrases that indicate ratings or evaluations

No Comments

No Known Activations