INDEX

Explanations

genre-specific phrases related to various types of movies and books

oai_token-act-pair · gpt-3.5-turbo

different genres of film, particularly thrillers, dramas, and role-playing games

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 recess

-0.81

ãĥĥãĥī

-0.76

cone

-0.73

baugh

-0.72

uchin

-0.71

 clot

-0.71

ividual

-0.69

yss

-0.68

greg

-0.68

aples

-0.68

POSITIVE LOGITS

 thriller

1.18

 sequel

1.09

 genre

1.05

 starring

0.90

 novelist

0.90

 comedy

0.87

 genres

0.85

sci

0.84

 satire

0.82

 horror

0.81

Activations Density 0.169%

genre-specific phrases related to various types of movies and books

different genres of film, particularly thrillers, dramas, and role-playing games

No Comments

No Known Activations