INDEX

Explanations

ratings given to various entities or items

oai_token-act-pair · gpt-3.5-turbo

instances of ratings or scores

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ansson

-0.87

adr

-0.82

working

-0.75

Alz

-0.75

coming

-0.73

ocrates

-0.73

filled

-0.66

ilus

-0.65

Tik

-0.65

ortun

-0.65

POSITIVE LOGITS

 rating

1.24

 ratings

1.18

 Ratings

1.08

 Rating

1.00

Rating

0.98

 rated

0.94

âĺħâĺħ

0.87

rating

0.79

 score

0.72

Beer

0.72

Activations Density 0.013%

ratings given to various entities or items

instances of ratings or scores

No Comments

No Known Activations