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

apixel

-0.74

buquerque

-0.68

 organisers

-0.66

avery

-0.65

 museum

-0.65

erey

-0.64

 Smithsonian

-0.64

 pacif

-0.64

 nonviolent

-0.63

oid

-0.63

POSITIVE LOGITS

fu

0.85

ãĥ¼ãĥĨ

0.70

loo

0.70

hoe

0.69

ãĥĥãĤ¯

0.68

Ð¼

0.67

âĶģ

0.67

ãĥ¼ãĤ¯

0.67

ifts

0.66

Fr

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.