INDEX

Explanations

various types or categories of things mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

references to various categories or classifications

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ITED

-0.70

NING

-0.68

 Mald

-0.61

IRO

-0.61

ometown

-0.61

ITNESS

-0.60

 Morning

-0.60

 Kenya

-0.59

Rio

-0.59

Hus

-0.58

POSITIVE LOGITS

etter

1.47

etting

1.46

faces

1.07

face

0.91

classes

0.88

isms

0.87

ahead

0.83

otypes

0.82

chool

0.81

linger

0.80

Activations Density 0.017%

various types or categories of things mentioned in the text

references to various categories or classifications

No Comments

No Known Activations