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

nces

-0.84

stretched

-0.72

nt

-0.68

DragonMagazine

-0.68

asar

-0.67

 actionGroup

-0.67

 constraints

-0.66

rat

-0.66

dal

-0.65

Write

-0.65

POSITIVE LOGITS

Pru

0.72

Zy

0.71

Lur

0.70

avez

0.70

 Onion

0.69

 Subway

0.68

 Hearing

0.67

 Salv

0.67

 Daesh

0.66

 Loot

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.