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

ãĥ¬

-0.70

 Phant

-0.68

ãĥĦ

-0.68

 Fract

-0.66

Ide

-0.66

 Plaza

-0.65

SLI

-0.64

 Preferences

-0.62

icio

-0.61

éĢ

-0.61

POSITIVE LOGITS

abor

0.73

chery

0.69

indle

0.68

indust

0.67

 sailors

0.66

oday

0.66

anmar

0.64

ertain

0.63

amera

0.62

legraph

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.