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

chedel

-0.82

 Rohing

-0.71

 ethic

-0.71

 persecuted

-0.71

)].

-0.71

 submar

-0.69

 antioxid

-0.67

 sailors

-0.66

apo

-0.65

CLASSIFIED

-0.65

POSITIVE LOGITS

istant

0.75

*/

0.72

speak

0.68

IGN

0.67

 Votes

0.65

DES

0.64

 Specifications

0.63

."

0.62

audi

0.61

DES

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.