INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

bleacher

-0.82

CTV

-0.71

OUR

-0.71

Arsenal

-0.69

UFC

-0.68

Loading

-0.68

fact

-0.68

adr

-0.67

 Trayvon

-0.67

thing

-0.66

POSITIVE LOGITS

osi

0.73

 Nose

0.73

illes

0.69

 Meadows

0.67

 peaks

0.63

soft

0.62

 lows

0.61

 Soft

0.61

aii

0.60

 Programs

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.