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

 Liberties

-0.70

entially

-0.69

uality

-0.62

 babys

-0.61

ISA

-0.61

 humiliated

-0.60

 fetus

-0.59

ually

-0.59

 Bran

-0.59

 Palest

-0.58

POSITIVE LOGITS

cean

0.70

cour

0.67

rogen

0.64

 Whitman

0.64

undred

0.64

zsche

0.63

 trending

0.62

ovsky

0.61

 notch

0.60

 suites

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.