INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

CHR

-0.85

SHARE

-0.81

Vari

-0.78

Flag

-0.77

Invalid

-0.77

Rating

-0.77

Benz

-0.76

ĻĤ

-0.73

Member

-0.71

ALL

-0.71

POSITIVE LOGITS

eele

0.84

atform

0.73

 Wonderland

0.69

mercial

0.69

zx

0.69

izing

0.67

 direction

0.67

CPC

0.65

merce

0.64

 dissemination

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.