INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

enegger

-0.70

ificate

-0.63

 volunte

-0.63

 behavi

-0.62

 Okin

-0.62

ographically

-0.61

onduct

-0.61

umbai

-0.61

 pione

-0.60

depth

-0.59

POSITIVE LOGITS

WA

0.72

bye

0.71

CCC

0.69

final

0.68

¥µ

0.67

Ã¼r

0.67

ADS

0.66

ãĥ´ãĤ¡

0.66

Fourth

0.61

ATER

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.