INDEX

Explanations

descriptions of physical appearance, specifically hair characteristics

oai_token-act-pair · gpt-3.5-turbo

descriptions of physical appearances and characteristics

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

nesday

-0.86

soDeliveryDate

-0.86

 Payments

-0.83

MAP

-0.82

relevant

-0.77

Recommend

-0.76

Players

-0.76

Reilly

-0.76

within

-0.76

ESA

-0.75

POSITIVE LOGITS

 beard

1.69

 tattoos

1.65

 mustache

1.63

 curly

1.52

 lips

1.44

 hair

1.39

 facial

1.39

 tits

1.38

 breasts

1.38

 eyebrows

1.36

Activations Density 0.319%

descriptions of physical appearance, specifically hair characteristics

descriptions of physical appearances and characteristics

No Known Activations