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

sync

-0.71

Pont

-0.69

////////////////////////////////

-0.68

aho

-0.68

etsk

-0.67

anse

-0.67

Bone

-0.67

 Petty

-0.66

 Sergeant

-0.66

Terror

-0.65

POSITIVE LOGITS

rongh

0.66

 Vita

0.65

$_

0.64

ESA

0.63

BMC

0.62

 devs

0.61

_-

0.60

ibrary

0.60

yles

0.60

izoph

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.