INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 surpr

-0.68

 proced

-0.67

 PROG

-0.66

encies

-0.64

 precedence

-0.64

İĭ

-0.63

 symm

-0.62

 unpop

-0.62

 proactive

-0.62

-|

-0.61

POSITIVE LOGITS

blade

0.72

0.69

çīĪ

0.68

ome

0.67

0.66

 Bagg

0.66

idav

0.65

0.64

Brave

0.64

culosis

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.