INDEX

Explanations

phrases related to a specific character named Eve, with a focus on details like actions she's performing or descriptions about her

oai_token-act-pair · gpt-3.5-turbo

the term "Eve" in 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

enegger

-0.83

Americans

-0.76

omo

-0.76

Downloadha

-0.70

ificent

-0.69

issue

-0.68

pmwiki

-0.68

ocard

-0.65

orage

-0.65

essee

-0.65

POSITIVE LOGITS

Eve

1.25

lyn

1.10

rette

1.09

lynn

0.92

ilon

0.89

 Valkyrie

0.86

Ens

0.78

eve

0.74

hammer

0.72

lla

0.71

Activations Density 0.005%

phrases related to a specific character named Eve, with a focus on details like actions she's performing or descriptions about her

the term "Eve" in various contexts

No Comments

No Known Activations