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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icle

-0.76

umerable

-0.73

auga

-0.72

 Turing

-0.68

selage

-0.68

iture

-0.67

utable

-0.66

usc

-0.66

 typew

-0.65

cephal

-0.64

POSITIVE LOGITS

 impunity

0.71

 Leah

0.69

 predict

0.66

Els

0.66

 Yose

0.64

 Marg

0.64

Wag

0.64

hips

0.63

 deregulation

0.63

Veg

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.