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

undo

-0.84

ilo

-0.76

cum

-0.74

catentry

-0.70

fect

-0.69

estyles

-0.67

gypt

-0.67

chery

-0.66

cill

-0.66

ong

-0.65

POSITIVE LOGITS

ulic

0.71

 Mechdragon

0.63

OPA

0.63

 Attacks

0.62

theless

0.61

 incumbent

0.61

 Shogun

0.61

 exerted

0.59

HB

0.59

 Pats

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.