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

oqu

-0.73

":"/

-0.72

acle

-0.71

raq

-0.70

rir

-0.68

acular

-0.67

acles

-0.67

itar

-0.67

 Boyle

-0.65

reason

-0.65

POSITIVE LOGITS

mson

0.73

 nomination

0.72

ividual

0.72

ADVERTISEMENT

0.68

 nominations

0.67

 dipping

0.63

 livest

0.63

ħĭ

0.63

 backfield

0.63

 nominee

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.