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

Sov

-0.85

 guiActiveUn

-0.74

 unfocusedRange

-0.73

-0.66

ocard

-0.66

¥

-0.64

actionDate

-0.64

izophren

-0.62

imir

-0.62

OUGH

-0.62

POSITIVE LOGITS

cov

0.77

 commanded

0.70

 raised

0.67

ached

0.63

 uncond

0.62

 independently

0.62

 preceded

0.61

eworthy

0.60

 introduced

0.60

 steered

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.