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

pri

-0.73

apixel

-0.69

 organise

-0.69

acy

-0.65

 organised

-0.61

omsky

-0.61

organ

-0.61

pez

-0.61

ycle

-0.61

rob

-0.60

POSITIVE LOGITS

ãģ®éŃĶ

0.78

gling

0.76

pmwiki

0.73

ãĤ¤ãĥĪ

0.71

Joined

0.70

 Inher

0.69

Ń·

0.68

 Convers

0.68

ADRA

0.67

 Marketable

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.