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

Negative Logits

bledon

-0.79

pherd

-0.69

achusetts

-0.69

Bei

-0.68

cffff

-0.68

selves

-0.67

izont

-0.66

raltar

-0.66

regon

-0.66

atever

-0.65

POSITIVE LOGITS

ably

0.78

ublic

0.76

wp

0.74

edd

0.68

kn

0.64

able

0.64

um

0.62

ables

0.62

ipes

0.62

tones

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.