INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 pipeline

-0.64

METHOD

-0.64

GM

-0.64

buff

-0.64

 bread

-0.63

 sourcing

-0.63

 workload

-0.62

 multiplier

-0.60

 grading

-0.59

email

-0.59

POSITIVE LOGITS

zona

0.96

iage

0.83

pire

0.75

aber

0.74

aden

0.72

zees

0.72

ugal

0.71

ihadi

0.70

itsch

0.70

cedes

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.