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

incial

-0.72

Ø³

-0.71

 sink

-0.71

omal

-0.70

atur

-0.66

²¾

-0.66

 unlucky

-0.65

ãĥĪ

-0.64

ãĥª

-0.62

ãĤ¤ãĥĪ

-0.61

POSITIVE LOGITS

LESS

0.83

...]

0.81

 Ended

0.70

hide

0.68

 Dragonbound

0.65

ivating

0.65

 Attention

0.64

nut

0.64

enment

0.62

Posts

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.