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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Marginal

-0.84

 Cosponsors

-0.82

iaries

-0.82

IAL

-0.78

OTOS

-0.77

Anonymous

-0.75

[+

-0.74

-0.72

Published

-0.69

BM

-0.68

POSITIVE LOGITS

 streaks

0.72

 Isles

0.72

 halfway

0.68

holes

0.64

sis

0.63

 Tend

0.62

 Bund

0.62

 bowl

0.62

ÃŁ

0.61

 Dream

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.