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

hower

-0.71

 Publication

-0.69

 Learned

-0.69

 WARN

-0.64

)].

-0.64

Dialogue

-0.63

rawdownloadcloneembedreportprint

-0.61

 UNCLASSIFIED

-0.61

-0.60

 paras

-0.59

POSITIVE LOGITS

port

0.72

Ó

0.70

wallet

0.66

vous

0.62

aughters

0.62

phabet

0.59

essing

0.59

vre

0.58

etsk

0.58

jri

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.