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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enaries

-0.84

uria

-0.80

winter

-0.78

ãĤ¦ãĤ¹

-0.77

aft

-0.73

abouts

-0.73

una

-0.73

isine

-0.71

fy

-0.71

unta

-0.71

POSITIVE LOGITS

ga

0.78

 obser

0.69

 Streaming

0.68

 cryst

0.67

Ky

0.67

Psy

0.66

 WHERE

0.64

GAM

0.63

Ga

0.61

 includ

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.