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

udeb

-0.69

traditional

-0.64

 Crusher

-0.61

aults

-0.61

rill

-0.60

uns

-0.60

pun

-0.59

gments

-0.59

metics

-0.59

 benchmarks

-0.58

POSITIVE LOGITS

soever

0.76

 RELE

0.76

APD

0.73

YR

0.70

AK

0.70

 ILCS

0.70

imony

0.67

 Defendants

0.67

ivism

0.66

Ô

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.