INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

clave

-0.92

rosse

-0.91

liga

-0.88

ilk

-0.83

yll

-0.82

aeus

-0.77

tile

-0.77

estamp

-0.76

marks

-0.76

tro

-0.74

POSITIVE LOGITS

 hoops

0.67

 catches

0.60

 Instr

0.59

 Bean

0.58

 catch

0.58

 spin

0.57

 emotions

0.57

ACP

0.57

 overc

0.56

 Sapphire

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.