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

externalActionCode

-0.78

ulia

-0.77

aja

-0.76

NW

-0.73

aci

-0.73

fed

-0.73

aun

-0.72

aida

-0.72

FA

-0.70

toe

-0.69

POSITIVE LOGITS

 pause

0.74

 Tempest

0.64

 implicit

0.61

 Coffin

0.61

 inference

0.61

orgetown

0.60

 irony

0.60

 sparing

0.59

grave

0.59

 explicitly

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.