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

numbered

-0.85

Haunted

-0.82

Jac

-0.72

ername

-0.72

Story

-0.71

bably

-0.70

Miss

-0.68

perfect

-0.66

eworthy

-0.65

Drag

-0.65

POSITIVE LOGITS

 bombers

0.77

 sacrific

0.71

zzo

0.67

 GOODMAN

0.66

 Shank

0.65

ãģ®éŃĶ

0.64

leck

0.64

 bomber

0.63

GW

0.62

onne

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.