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

ãģ®éŃĶ

-0.71

analy

-0.61

Raw

-0.60

é¾įå¥ĳå£«

-0.60

MPs

-0.60

tics

-0.59

 Pepper

-0.58

step

-0.58

 shudder

-0.57

 clamp

-0.57

POSITIVE LOGITS

fortune

0.81

 livest

0.77

gerald

0.75

ufact

0.73

ccording

0.70

mble

0.70

 Gutenberg

0.70

sea

0.69

 horm

0.69

restrial

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.