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

 ILCS

-0.71

velop

-0.70

augh

-0.70

ophile

-0.69

olog

-0.64

 royalties

-0.63

natureconservancy

-0.62

parts

-0.60

ople

-0.60

kb

-0.59

POSITIVE LOGITS

SPI

0.68

 Kislyak

0.66

BLIC

0.66

({

0.65

imum

0.64

 bias

0.63

rium

0.62

icago

0.61

 Higgins

0.60

Russ

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.