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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lus

-0.73

owler

-0.67

lie

-0.66

aily

-0.65

_-

-0.62

ummer

-0.62

 worse

-0.62

oko

-0.61

 kicker

-0.61

 Genius

-0.60

POSITIVE LOGITS

ItemTracker

0.74

 Died

0.71

ortium

0.65

emetery

0.65

Includes

0.64

 mixes

0.64

 Ended

0.64

 Reached

0.63

xtap

0.62

 INCLUD

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.