INDEX

Explanations

mentions of various characters, likely from a puppet show, and specific scenes or details associated with them

oai_token-act-pair · gpt-3.5-turbo

references to puppetry and puppet shows

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

ept

-0.82

Benz

-0.81

ascus

-0.80

Sov

-0.80

Islamic

-0.78

Assad

-0.78

Sov

-0.77

hene

-0.75

Iraq

-0.75

 benz

-0.75

POSITIVE LOGITS

 cartoons

1.55

 cartoon

1.54

 mascot

1.49

 Simpsons

1.44

 Cartoon

1.41

 Sponge

1.39

Moe

1.38

 Toad

1.37

 masc

1.34

 Balloon

1.34

Activations Density 0.576%

mentions of various characters, likely from a puppet show, and specific scenes or details associated with them

references to puppetry and puppet shows

No Comments

No Known Activations