INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

rugged

-0.78

usha

-0.74

anth

-0.74

 Huss

-0.72

oster

-0.67

ancies

-0.67

istically

-0.67

Zah

-0.65

 Vega

-0.64

Lex

-0.64

POSITIVE LOGITS

hift

0.78

gram

0.72

 Motion

0.68

IRED

0.68

JECT

0.67

 Stores

0.66

Revolution

0.66

 Recorded

0.65

ĨĴ

0.64

ailability

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.