INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

watch

-0.84

onte

-0.78

aire

-0.74

ardless

-0.73

oise

-0.72

doors

-0.70

encer

-0.69

orio

-0.69

ixt

-0.68

iframe

-0.68

POSITIVE LOGITS

 misunder

0.92

 depreciation

0.67

 deval

0.66

 subsequ

0.65

 curses

0.64

 invaluable

0.63

 mathemat

0.63

rab

0.63

 mish

0.62

jer

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.