INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

åĳ

-0.83

-0.71

Merit

-0.68

material

-0.67

Sov

-0.67

 Cortex

-0.66

border

-0.65

çĦ

-0.64

ãĥĺ

-0.63

bg

-0.63

POSITIVE LOGITS

idad

0.70

psons

0.69

enne

0.68

 Wasserman

0.66

 Elias

0.64

essen

0.62

oken

0.62

 SPORTS

0.61

kees

0.61

ionics

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.