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

SPONSORED

-0.69

Lens

-0.66

vacc

-0.66

oiler

-0.65

STON

-0.65

Narr

-0.64

 Alam

-0.64

alin

-0.64

esson

-0.63

\.

-0.63

POSITIVE LOGITS

jri

0.80

ebus

0.76

 Ogre

0.75

 Polaris

0.74

pse

0.73

 Firm

0.72

 compr

0.71

rices

0.65

etheus

0.64

anamo

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.