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

ittees

-0.82

 Loot

-0.76

aneers

-0.74

olicy

-0.72

 Syndicate

-0.70

netflix

-0.70

 loot

-0.66

Glass

-0.65

ItemTracker

-0.63

 raiding

-0.62

POSITIVE LOGITS

izer

0.70

xual

0.70

 diabetic

0.70

izes

0.69

 youngster

0.67

baugh

0.64

 subp

0.63

éĹ

0.63

ises

0.62

ovich

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.