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

 lick

-0.70

veyard

-0.70

hower

-0.68

phis

-0.68

 Ghost

-0.67

 Chiefs

-0.67

 Nether

-0.66

isode

-0.66

#$

-0.66

ns

-0.65

POSITIVE LOGITS

Adams

0.79

 bureau

0.70

ciplinary

0.65

REF

0.65

ãĥ´ãĤ¡

0.64

Viol

0.63

 goodwill

0.61

sonian

0.61

Article

0.60

artisan

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.