INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

iors

-0.84

è¦ļéĨĴ

-0.76

iffs

-0.74

isations

-0.72

OAD

-0.69

TL

-0.69

\">

-0.67

Oak

-0.67

idates

-0.66

isks

-0.65

POSITIVE LOGITS

 Palestin

0.73

 looph

0.72

 Divinity

0.70

 culp

0.69

 scattering

0.68

 fracturing

0.67

 crush

0.67

stanbul

0.66

 fortun

0.65

ysis

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.