INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ById

-0.91

Wr

-0.77

FontSize

-0.76

 heirs

-0.63

 inherit

-0.63

Gro

-0.61

Zero

-0.61

 Dept

-0.60

uana

-0.60

witch

-0.60

POSITIVE LOGITS

ussions

0.82

 Surviv

0.69

emi

0.68

etheless

0.67

 tsunami

0.64

existing

0.64

comings

0.62

enture

0.60

 descriptive

0.60

rities

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.