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

atus

-0.77

hern

-0.70

 Spiral

-0.68

å¦

-0.68

ibly

-0.67

hest

-0.67

ibia

-0.66

irtual

-0.65

BILITIES

-0.64

itbart

-0.64

POSITIVE LOGITS

 destination

0.71

#$

0.66

 someday

0.66

 climax

0.63

 destinations

0.63

dayName

0.61

 circ

0.59

eworld

0.59

flo

0.59

 designer

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.