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

-0.80

Choice

-0.75

hops

-0.73

lease

-0.70

undown

-0.70

abc

-0.68

hani

-0.68

Books

-0.67

luck

-0.67

cci

-0.67

POSITIVE LOGITS

 martyr

0.73

ocaust

0.68

Pax

0.68

 defeat

0.68

 quart

0.68

mere

0.66

 savior

0.66

 cripp

0.65

Magn

0.63

 wonders

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.