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

PLIED

-0.76

 Vaughan

-0.69

TOR

-0.69

actionDate

-0.68

Chart

-0.66

 Rowe

-0.65

urbed

-0.63

urai

-0.62

aleb

-0.61

endants

-0.60

POSITIVE LOGITS

enegger

0.72

 rule

0.68

sburg

0.67

uese

0.65

 reun

0.63

\\\\

0.61

 Dialogue

0.60

Truth

0.59

 Unle

0.57

 Competition

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.