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

ository

-0.70

ership

-0.66

Dialog

-0.65

gradient

-0.65

ensibly

-0.63

enhagen

-0.61

querque

-0.61

 heir

-0.61

sterdam

-0.61

WER

-0.60

POSITIVE LOGITS

Best

0.72

ests

0.70

...]

0.67

ities

0.65

pa

0.63

eger

0.63

 aboard

0.63

Gaza

0.63

Hob

0.62

icas

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.