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

 Johann

-0.68

lement

-0.63

 Restoration

-0.61

 comprehens

-0.59

 Fifty

-0.59

 Trident

-0.58

 herald

-0.58

 Babel

-0.58

 seismic

-0.57

 ballet

-0.57

POSITIVE LOGITS

iour

0.84

asca

0.81

ADS

0.77

CDC

0.73

AX

0.70

quit

0.69

hovah

0.69

inelli

0.69

gov

0.68

NV

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.