INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ishing

-0.71

finder

-0.69

rets

-0.68

ITION

-0.67

Ey

-0.67

ishes

-0.67

ocr

-0.66

DAY

-0.63

Skin

-0.62

RGB

-0.61

POSITIVE LOGITS

ãĥĲ

0.88

phabet

0.87

Äį

0.80

xual

0.75

ËĪ

0.74

 Moff

0.71

ussen

0.70

 è£ıç

0.69

 Gors

0.68

join

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.