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

olicy

-0.79

andise

-0.75

 withd

-0.70

icity

-0.70

ounty

-0.67

alf

-0.67

imore

-0.66

erity

-0.66

kefeller

-0.65

 EntityItem

-0.64

POSITIVE LOGITS

gnu

0.68

ĪĴ

0.67

bugs

0.65

hus

0.65

lyak

0.64

VI

0.64

ĺħ

0.63

ims

0.62

 Introduced

0.61

 Helpful

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.