INDEX

Explanations

references to comic book superheroes, especially Captain America

oai_token-act-pair · gpt-3.5-turbo

references to "Captain America" and associated characters or films

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 conven

-0.69

mediate

-0.66

tem

-0.65

eret

-0.65

 sponsor

-0.65

zl

-0.64

GBT

-0.62

 trough

-0.62

wee

-0.62

housing

-0.62

POSITIVE LOGITS

 Awakens

0.87

âĦ¢:

0.86

 trilogy

0.80

 Armored

0.80

ences

0.79

 Investigations

0.76

 Creed

0.75

 Mansion

0.74

Â®,

0.74

ioxide

0.74

Activations Density 0.037%

references to comic book superheroes, especially Captain America

references to "Captain America" and associated characters or films

No Comments

No Known Activations