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

 Conquest

-0.76

 Awakening

-0.75

Unity

-0.73

 Ranked

-0.67

 Craw

-0.66

 Equality

-0.65

 Invasion

-0.65

 Discovery

-0.65

 Passion

-0.62

POSITIVE LOGITS

rily

0.79

isch

0.74

amine

0.71

itably

0.70

nas

0.70

 Andersen

0.66

urally

0.65

ieu

0.65

ero

0.64

versely

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.