INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

milo

-0.80

Magikarp

-0.75

NPR

-0.75

Merit

-0.74

heid

-0.72

 theirs

-0.71

rights

-0.69

 minded

-0.65

BILITY

-0.65

 hers

-0.64

POSITIVE LOGITS

nell

0.74

[]

0.73

 quantity

0.63

~/.

0.61

ead

0.61

 Cities

0.61

 Summary

0.60

usra

0.59

autions

0.58

agna

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.