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

 reserv

-0.70

iors

-0.68

 Reserve

-0.66

ality

-0.66

 favour

-0.64

 Committees

-0.64

iod

-0.63

 favor

-0.63

arity

-0.62

 Ratio

-0.61

POSITIVE LOGITS

Adams

0.83

00200000

0.78

âĶĢâĶĢâĶĢâĶĢ

0.75

encer

0.74

 âĩ

0.72

 è£ıè¦ļéĨĴ

0.70

inez

0.69

osta

0.68

 POLITICO

0.68

?]

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.