INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

weekly

-0.77

ioxide

-0.67

WR

-0.65

azine

-0.65

esc

-0.65

Neil

-0.63

fix

-0.63

 forg

-0.62

ologne

-0.62

edy

-0.62

POSITIVE LOGITS

ãĥ¼ãĤ¯

0.86

 "$:/

0.83

 Badge

0.69

tained

0.66

ãĥ¼ãĥ

0.65

gdala

0.62

 illusions

0.62

Course

0.61

withstanding

0.61

 possessions

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.