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

 assassinated

-0.76

 Hancock

-0.73

bip

-0.73

isma

-0.72

engu

-0.71

auld

-0.68

trip

-0.67

caps

-0.66

ilot

-0.65

Cho

-0.64

POSITIVE LOGITS

acion

0.69

orld

0.68

 rehab

0.64

fav

0.64

ifferent

0.64

 msec

0.63

 batters

0.63

teness

0.61

 infield

0.58

 warr

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.