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

 Shant

-0.75

 Mord

-0.74

spr

-0.66

Dir

-0.63

 dawn

-0.63

 Shap

-0.62

topia

-0.61

 emer

-0.60

 adulthood

-0.60

assisted

-0.60

POSITIVE LOGITS

 incent

0.85

oir

0.83

 econom

0.76

emouth

0.76

BIL

0.73

ewitness

0.73

ADRA

0.70

_-

0.68

olics

0.68

nesota

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.