INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 ensu

-0.77

 Citiz

-0.69

 millenn

-0.69

 thorough

-0.68

 unden

-0.64

 disag

-0.62

 acknow

-0.62

 Instr

-0.62

 mathemat

-0.61

 occas

-0.61

POSITIVE LOGITS

liest

0.82

angled

0.81

atics

0.80

uble

0.76

cean

0.73

lesi

0.71

lings

0.71

iety

0.71

nings

0.70

itudes

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.