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

DonaldTrump

-0.80

 sterling

-0.71

ISC

-0.70

oulos

-0.69

 virt

-0.68

iscons

-0.65

 ambassador

-0.64

ollower

-0.64

utherford

-0.63

icy

-0.62

POSITIVE LOGITS

zeb

0.75

uda

0.72

qi

0.72

lined

0.69

NetMessage

0.69

aby

0.68

lines

0.68

mint

0.67

bee

0.66

 directions

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.