INDEX

Explanations

No Explanations Found

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

æĪ¦

-0.72

cair

-0.71

aq

-0.70

 Saud

-0.67

OPER

-0.66

INTON

-0.66

ÃŁ

-0.65

ATER

-0.65

ror

-0.65

ascript

-0.65

POSITIVE LOGITS

 actionGroup

0.70

pressed

0.69

roots

0.69

 brim

0.68

blu

0.65

elight

0.62

eared

0.61

 speaking

0.61

emo

0.61

fired

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.