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

hend

-0.76

Gir

-0.70

 Kier

-0.70

oute

-0.69

steen

-0.69

Lak

-0.69

 Santos

-0.66

 Starship

-0.64

 Rafael

-0.64

 Virgin

-0.64

POSITIVE LOGITS

natureconservancy

0.86

essions

0.71

atorial

0.69

orset

0.68

dayName

0.66

 Occupations

0.65

achelor

0.64

umin

0.64

 fixme

0.64

 restraining

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.