INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

til

-0.80

vig

-0.69

 Viper

-0.69

Interstitial

-0.68

 punishable

-0.66

Ul

-0.62

sth

-0.61

 Taxi

-0.61

Narr

-0.61

ACTED

-0.60

POSITIVE LOGITS

eeks

0.76

zik

0.69

ourn

0.68

conservancy

0.68

wic

0.67

icio

0.67

leys

0.65

eport

0.65

itudes

0.65

ek

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.