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

 dracon

-0.75

rend

-0.74

furt

-0.68

Ħ¢

-0.67

roach

-0.67

rition

-0.66

 challeng

-0.66

 appre

-0.66

cs

-0.66

 dilig

-0.65

POSITIVE LOGITS

atum

0.80

 sshd

0.75

ãĥ¼ãĥ³

0.74

NCT

0.74

authorized

0.63

 Membership

0.62

 Archives

0.62

 Airport

0.59

 Hedge

0.59

 annex

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.