INDEX

Explanations

references to lips and related actions or characteristics

oai_token-act-pair · gpt-3.5-turbo

terms related to lips and lip treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

organized

-0.63

Games

-0.61

 organized

-0.60

 Division

-0.60

Bu

-0.59

Catalog

-0.58

 Bowman

-0.58

rient

-0.58

Information

-0.57

uable

-0.57

POSITIVE LOGITS

 lips

4.05

 tongues

2.00

 mouths

1.99

 mouth

1.90

 cheeks

1.89

lip

1.87

 tongue

1.66

 jaws

1.51

 lipstick

1.50

 eyebrows

1.42

Activations Density 0.020%

references to lips and related actions or characteristics

terms related to lips and lip treatments

No Comments

No Known Activations