INDEX

Explanations

terms related to science fiction (sci-fi)

oai_token-act-pair · gpt-3.5-turbo

references to science fiction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

lain

-0.97

LIA

-0.68

theless

-0.64

 Chambers

-0.60

 Clerk

-0.58

hillary

-0.58

 weights

-0.56

xual

-0.55

 Curve

-0.54

HRC

-0.54

POSITIVE LOGITS

fi

1.02

ampunk

0.88

fiction

0.88

 fiction

0.87

Fi

0.81

antically

0.81

antasy

0.81

atic

0.79

acly

0.78

apist

0.77

Activations Density 0.029%

terms related to science fiction (sci-fi)

references to science fiction

No Comments

No Known Activations