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

meg

-0.70

phans

-0.69

spin

-0.68

ãĤ¨

-0.67

rollers

-0.67

mph

-0.67

mop

-0.66

osaurs

-0.66

mx

-0.66

mill

-0.65

POSITIVE LOGITS

 challeng

0.74

 describ

0.73

 appropriate

0.67

 pled

0.66

 deline

0.66

 philosoph

0.64

 toile

0.63

tyr

0.63

vou

0.61

 consulted

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.