INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ovember

-0.69

olean

-0.68

vention

-0.66

Timeout

-0.62

 Coch

-0.62

 orbit

-0.61

 "$:/

-0.61

ire

-0.61

 sediment

-0.61

Cla

-0.59

POSITIVE LOGITS

 incompet

0.67

Transfer

0.66

medium

0.66

 misdem

0.65

 Malays

0.65

asel

0.65

uploads

0.65

ICS

0.63

ELL

0.63

 complying

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.