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

ART

-0.70

exec

-0.67

arter

-0.65

uay

-0.65

]'

-0.64

 overfl

-0.64

Break

-0.64

MB

-0.59

Ń·

-0.58

ARR

-0.58

POSITIVE LOGITS

pected

0.69

ailability

0.68

soDeliveryDate

0.67

 captcha

0.66

YL

0.65

hene

0.65

udeau

0.64

phalt

0.64

utic

0.64

plings

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.