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

ãĥĺ

-0.71

eas

-0.67

hed

-0.67

itÃ©

-0.66

 unintention

-0.66

weet

-0.64

illus

-0.64

achev

-0.64

rites

-0.63

mouse

-0.63

POSITIVE LOGITS

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

0.75

âĶĢâĶĢâĶĢâĶĢ

0.73

 chapel

0.64

assies

0.62

opter

0.60

glers

0.60

 newsletters

0.58

":[{"

0.58

 cartels

0.58

 patronage

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.