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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

manship

-0.78

sector

-0.76

sequence

-0.74

portion

-0.73

>[

-0.71

ounces

-0.69

eva

-0.68

foundation

-0.67

chrome

-0.67

worthiness

-0.66

POSITIVE LOGITS

omas

0.75

 orbit

0.72

dos

0.69

tee

0.69

adish

0.67

anto

0.66

 noon

0.66

 cradle

0.66

aito

0.64

ween

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.