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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ģĸ

-0.90

ights

-0.73

 Reprodu

-0.70

erial

-0.69

ingu

-0.67

chwitz

-0.66

ird

-0.66

issions

-0.66

adobe

-0.65

oe

-0.64

POSITIVE LOGITS

 timetable

0.69

 Vaugh

0.63

 Brist

0.62

 sqor

0.61

youtu

0.60

quickShipAvailable

0.59

leading

0.59

leaders

0.58

leader

0.58

 suspensions

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.