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

 è£ıè

-0.69

 Abedin

-0.68

 Liang

-0.67

adra

-0.66

 wielding

-0.64

lessly

-0.63

 cooker

-0.62

 Carlson

-0.62

 Reyes

-0.62

bom

-0.62

POSITIVE LOGITS

iversary

0.72

++++++++

0.70

usions

0.69

VIS

0.68

ndum

0.67

IVERS

0.66

sylv

0.65

########

0.62

irements

0.62

akedown

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.