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

berra

-0.78

rex

-0.67

 srfAttach

-0.67

TOP

-0.66

ovember

-0.64

Islamic

-0.63

rug

-0.63

 convol

-0.63

duc

-0.62

atform

-0.62

POSITIVE LOGITS

kaya

0.77

 Notes

0.66

ealous

0.66

alled

0.66

olitan

0.63

ea

0.63

 EntityItem

0.62

enstein

0.62

ives

0.61

ultan

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.