INDEX

Explanations

mentions of the name "Dat" followed by numerical values

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

entric

-0.78

ittal

-0.72

Ô

-0.68

ADE

-0.66

ing

-0.66

 figure

-0.64

HAM

-0.64

ãģĨ

-0.63

":""},{"

-0.63

POSITIVE LOGITS

ihad

0.88

awan

0.79

imes

0.76

abases

0.76

ifa

0.75

ullah

0.73

emp

0.73

ween

0.70

tered

0.70

TPS

0.70

Activations Density 0.069%

mentions of the name "Dat" followed by numerical values

No Comments

No Known Activations