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

 Fernandez

-0.71

 Ramos

-0.67

ylum

-0.65

Mas

-0.64

 Wolfgang

-0.63

Xi

-0.62

atown

-0.62

imil

-0.61

aurus

-0.61

ngth

-0.59

POSITIVE LOGITS

theless

0.81

culosis

0.70

gh

0.68

è¦ļéĨĴ

0.68

 Flavoring

0.64

cca

0.63

 prope

0.62

 appre

0.62

gat

0.60

 sqor

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.