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

uckland

-0.96

ongo

-0.81

aton

-0.77

uti

-0.75

è¦ļéĨĴ

-0.74

urst

-0.73

ALT

-0.73

illed

-0.72

Definition

-0.71

rix

-0.70

POSITIVE LOGITS

 Bake

0.66

 Sorce

0.66

FTWARE

0.66

 Resp

0.66

 Gear

0.64

ifiers

0.63

 HDMI

0.62

Toy

0.62

Rez

0.62

 Oculus

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.