INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

itative

-0.80

iating

-0.78

legged

-0.69

olving

-0.65

serving

-0.62

rooms

-0.61

idity

-0.61

esides

-0.60

orescence

-0.59

ulative

-0.59

POSITIVE LOGITS

 Emin

0.79

luaj

0.73

cia

0.70

ERO

0.70

nces

0.70

Iv

0.69

 Vald

0.68

thia

0.64

Magn

0.63

 Documents

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.