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

 crates

-0.76

¶ħ

-0.75

 crow

-0.74

 subsequ

-0.73

 pudding

-0.72

 duct

-0.72

 appropri

-0.71

pul

-0.71

apy

-0.71

 plaus

-0.68

POSITIVE LOGITS

emphasis

0.86

Cast

0.85

NAT

0.85

July

0.84

Fel

0.81

same

0.81

Ranked

0.80

Irish

0.80

Ireland

0.79

hitting

0.79

Activations Density 0.000%

No Known Activations

This feature has no known activations.