INDEX

Explanations

words related to transformation and change processes

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

references to animated shows and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

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

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_post

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

Sov

-0.98

 MDMA

-0.88

raped

-0.84

Sov

-0.81

 doping

-0.81

DPR

-0.78

 wines

-0.78

inav

-0.78

afia

-0.77

 Lavrov

-0.77

POSITIVE LOGITS

 Cartoon

1.78

 cartoons

1.75

 cartoon

1.71

 Simpsons

1.65

 Pixar

1.56

 Garfield

1.47

 animated

1.45

 Animated

1.42

 mascot

1.41

 Sponge

1.39

Activations Density 0.577%

words related to transformation and change processes

references to animated shows and their characteristics

No Comments

No Known Activations