INDEX

Explanations

references to the superhero character "Captain America" in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of "Captain" from various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

td

-0.79

pher

-0.75

itual

-0.72

itsch

-0.71

âĶģ

-0.68

practice

-0.66

elf

-0.65

ilateral

-0.65

ocene

-0.64

POSITIVE LOGITS

 Captain

1.02

ĨĴ

0.88

Captain

0.87

 Kidd

0.81

berries

0.80

berry

0.78

 Marvel

0.78

 Marshal

0.78

 Colonel

0.77

 Jack

0.77

Activations Density 0.009%

references to the superhero character "Captain America" in various contexts

mentions of "Captain" from various contexts

No Comments

No Known Activations