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

geries

-0.74

Ô

-0.72

Ò

-0.72

ewater

-0.70

Ì¶

-0.68

 disadvant

-0.68

ocene

-0.68

ources

-0.66

ingly

-0.66

IVES

-0.66

POSITIVE LOGITS

ÃĹ

0.60

eon

0.60

ARC

0.59

 Advent

0.59

 Fatal

0.59

 Clover

0.58

CLR

0.57

htt

0.57

arson

0.56

 warp

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.