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

²¾

-0.70

tainment

-0.69

 attribution

-0.67

ogyn

-0.64

ãĥĨ

-0.63

 Attribution

-0.62

icter

-0.62

hazard

-0.61

monary

-0.61

POSITIVE LOGITS

uras

0.79

theless

0.75

 Barnett

0.68

 Wilkinson

0.66

 Gardner

0.64

 Osborne

0.64

 Christensen

0.63

hester

0.63

 REALLY

0.63

 Pratt

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.