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

CHAPTER

-0.79

ners

-0.76

Hack

-0.72

 Izan

-0.71

lla

-0.70

Alias

-0.68

 Hills

-0.66

oiler

-0.66

IELD

-0.64

Exit

-0.64

POSITIVE LOGITS

querque

0.72

merce

0.69

cffff

0.67

trak

0.65

geoning

0.65

*/(

0.65

 subpoen

0.64

rss

0.62

conservancy

0.62

nab

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.