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

hovah

-0.87

vironment

-0.72

wolves

-0.65

Ü

-0.65

McM

-0.64

anasia

-0.64

icidal

-0.62

Ħ¢

-0.62

 proletariat

-0.61

izabeth

-0.61

POSITIVE LOGITS

orate

0.75

netflix

0.74

 hinges

0.69

DN

0.66

 Span

0.65

 sidel

0.63

jri

0.62

Teg

0.61

orp

0.60

 understatement

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.