INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 supers

-0.64

 Centauri

-0.63

 ORDER

-0.62

 Sidd

-0.61

^^

-0.60

GBT

-0.60

 Typh

-0.59

sq

-0.59

 integrates

-0.58

 Reborn

-0.58

POSITIVE LOGITS

oneliness

0.84

icians

0.83

nikov

0.82

luck

0.77

olitan

0.75

 Monica

0.74

dor

0.74

ney

0.73

nik

0.73

ologue

0.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.