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

Not in Any Lists

No Comments

Negative Logits

usterity

-0.67

 Shark

-0.66

mong

-0.65

 antioxid

-0.65

iatus

-0.65

 disse

-0.64

Clock

-0.64

ikers

-0.63

azy

-0.62

ALS

-0.61

POSITIVE LOGITS

ç¥ŀ

0.69

oji

0.66

 merits

0.64

ãĥĺãĥ©

0.64

ilipp

0.63

ibel

0.62

iae

0.60

Mex

0.60

ãĢĳ

0.60

ivation

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.