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

 livest

-0.69

 roam

-0.67

ply

-0.64

 Parish

-0.62

 Bake

-0.61

aney

-0.58

Reloaded

-0.58

od

-0.57

 closed

-0.57

Reilly

-0.57

POSITIVE LOGITS

upt

0.83

zon

0.80

opal

0.78

chel

0.77

 Debor

0.76

eret

0.76

utor

0.75

obal

0.74

gc

0.74

ocracy

0.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.