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

ledged

-0.77

oing

-0.71

answer

-0.69

omore

-0.69

rency

-0.68

andering

-0.68

 lash

-0.68

ittal

-0.67

hooting

-0.66

retch

-0.65

POSITIVE LOGITS

UID

0.79

 Eggs

0.76

UID

0.67

 UEFA

0.65

 Tome

0.63

Master

0.62

 Tayyip

0.61

Fra

0.61

Du

0.60

 CARD

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.