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

 primed

-0.69

interstitial

-0.68

alde

-0.64

 counted

-0.63

 prim

-0.62

prim

-0.61

 gestation

-0.61

ishers

-0.60

 magnification

-0.60

furt

-0.59

POSITIVE LOGITS

pmwiki

0.76

ussie

0.73

itches

0.73

thur

0.70

WB

0.69

ombat

0.67

_(

0.67

Blu

0.66

lations

0.66

yrim

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.