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

ICO

-0.77

Delivery

-0.73

uploads

-0.71

idency

-0.70

CE

-0.70

IME

-0.68

izzle

-0.67

iqueness

-0.67

payment

-0.66

ilee

-0.66

POSITIVE LOGITS

entin

0.77

 Pose

0.69

eteria

0.66

 Battalion

0.66

 Rasm

0.65

 Thermal

0.65

 Scientific

0.64

 Offense

0.63

 Amend

0.63

 Todd

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.