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

OME

-0.81

Â¯Â¯Â¯Â¯

-0.70

ŀ

-0.67

edia

-0.67

ĺħ

-0.64

Ü

-0.64

 Holiday

-0.63

Ĳ

-0.62

icle

-0.62

Dead

-0.62

POSITIVE LOGITS

hood

0.77

devices

0.72

 regards

0.68

ULT

0.68

 diapers

0.65

abolic

0.62

 clot

0.61

ppers

0.59

 laun

0.59

alysis

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.