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

don

-0.76

çİĭ

-0.76

prototype

-0.73

Construct

-0.72

bending

-0.71

CONCLUS

-0.69

tests

-0.68

 princip

-0.67

Amazing

-0.67

scrib

-0.65

POSITIVE LOGITS

 Rouge

0.73

FN

0.70

IPM

0.68

 Exit

0.67

 Bruins

0.65

LW

0.64

CNS

0.62

LH

0.62

 Lans

0.61

 Polo

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.