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

itionally

-0.76

unker

-0.75

NetMessage

-0.75

ulk

-0.71

Ü

-0.69

artney

-0.69

rarily

-0.66

itially

-0.66

 inertia

-0.66

 Almighty

-0.63

POSITIVE LOGITS

 Lans

0.75

fighter

0.72

rious

0.71

 buds

0.69

 Derby

0.68

 Solitaire

0.66

 ACTIONS

0.65

bred

0.62

pora

0.61

flies

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.