INDEX

Explanations

keywords related to television dramas

oai_token-act-pair · gpt-3.5-turbo

references to dramatic works or productions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ovo

-0.91

 redistributed

-0.76

achev

-0.70

aton

-0.70

laws

-0.70

anza

-0.70

ossier

-0.69

arching

-0.67

choes

-0.67

azar

-0.66

POSITIVE LOGITS

 drama

1.00

 queens

0.99

 dramas

0.97

 queen

0.81

 unfold

0.80

 Drama

0.77

 Reign

0.75

 revolving

0.73

 airs

0.72

 comed

0.70

Activations Density 0.014%

keywords related to television dramas

references to dramatic works or productions

No Comments

No Known Activations