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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 largeDownload

-0.73

 Battalion

-0.68

ttp

-0.65

igham

-0.64

ideos

-0.63

set

-0.63

spot

-0.62

oyd

-0.59

Record

-0.58

Pac

-0.58

POSITIVE LOGITS

 Parenthood

0.73

Fey

0.65

 hacks

0.64

 perish

0.62

ARDIS

0.61

 Bits

0.61

 trunk

0.61

GES

0.61

 jQuery

0.60

ģĸ

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.