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

 reclaimed

-0.81

 precip

-0.74

unal

-0.74

 stabilized

-0.69

 interchangeable

-0.67

egal

-0.65

 irreversible

-0.65

 conventional

-0.65

thr

-0.65

 electrodes

-0.62

POSITIVE LOGITS

 Restaur

0.72

ï¸

0.72

Boo

0.69

 likeness

0.66

 Tuls

0.61

 Islanders

0.60

Letter

0.60

isin

0.60

gie

0.60

 Winn

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.