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

HB

-0.76

enhagen

-0.71

ropolis

-0.71

Tea

-0.70

amaz

-0.69

adata

-0.69

utical

-0.67

pedia

-0.66

isance

-0.66

alian

-0.65

POSITIVE LOGITS

 veter

0.74

ELF

0.74

xual

0.72

 rounded

0.70

 fired

0.70

 athlet

0.65

istar

0.65

 unemploy

0.65

 firing

0.65

 overcl

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.