INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

adj

-0.76

aft

-0.65

ãĥĩãĤ£

-0.63

 Kenobi

-0.63

wed

-0.62

luster

-0.62

Jed

-0.62

 Weir

-0.62

otom

-0.61

maj

-0.61

POSITIVE LOGITS

 Bild

0.68

ICO

0.64

 regards

0.63

esta

0.63

 Lect

0.62

 misunderstand

0.62

ĸļ

0.62

 Rolls

0.61

 Behavioral

0.61

 Shiv

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.