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

MW

-0.76

ipel

-0.71

ocobo

-0.68

CSS

-0.68

FY

-0.68

izzy

-0.67

cloth

-0.66

neau

-0.66

grain

-0.65

hler

-0.65

POSITIVE LOGITS

stood

0.67

 Jarvis

0.67

 horizont

0.64

abama

0.64

andr

0.62

 --------------------

0.60

itability

0.59

 scrimmage

0.58

adv

0.58

RU

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.