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

ãĢ

-0.79

igil

-0.72

entin

-0.71

rome

-0.69

microsoft

-0.68

atican

-0.67

emonic

-0.67

éŃĶ

-0.65

olon

-0.64

è¦ļéĨĴ

-0.64

POSITIVE LOGITS

videos

0.69

ask

0.65

mort

0.63

 elig

0.61

earchers

0.60

Average

0.60

 Saturdays

0.59

 valleys

0.59

 McCabe

0.58

poll

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.