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

cko

-0.69

itored

-0.67

culosis

-0.64

 Mills

-0.64

 Shack

-0.63

 Powers

-0.61

tec

-0.61

keys

-0.61

 veins

-0.60

anooga

-0.60

POSITIVE LOGITS

ãĥīãĥ©ãĤ´ãĥ³

0.85

 forgiven

0.75

FUN

0.75

éĹ

0.69

ACTION

0.67

å¥³

0.67

FER

0.67

/$

0.66

 æľ

0.65

ingo

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.