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

ifacts

-0.74

Beta

-0.67

DERR

-0.65

mentation

-0.65

 Amin

-0.65

ournal

-0.63

atform

-0.63

ription

-0.62

Armor

-0.61

imilation

-0.60

POSITIVE LOGITS

 debit

0.63

liam

0.63

tera

0.63

 stead

0.62

 Visa

0.62

dden

0.61

 unlimited

0.61

 sponsor

0.60

dfx

0.59

 waive

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.