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

ancial

-0.74

selage

-0.74

milo

-0.72

imet

-0.71

ze

-0.68

 Upgrade

-0.67

 init

-0.63

ppa

-0.63

 Helpful

-0.62

 sliced

-0.62

POSITIVE LOGITS

NF

0.76

ENTS

0.76

SON

0.75

TOP

0.74

UGC

0.73

throp

0.73

 propensity

0.71

MO

0.70

ELD

0.70

LD

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.