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

uni

-0.84

atham

-0.80

ournals

-0.75

asm

-0.74

ipe

-0.73

uchi

-0.70

otine

-0.69

 Yorkshire

-0.69

nee

-0.69

orough

-0.68

POSITIVE LOGITS

arded

0.67

 Dangerous

0.67

 resisted

0.64

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.63

@@@@

0.63

 contraceptives

0.61

ailability

0.61

 DEFENSE

0.61

 shielding

0.61

 shroud

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.