INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

SPONSORED

-0.74

keepers

-0.68

pillar

-0.65

Sham

-0.64

ATTLE

-0.63

Pool

-0.62

void

-0.61

cluded

-0.60

nai

-0.59

skip

-0.59

POSITIVE LOGITS

umatic

0.71

ollah

0.70

htaking

0.70

 eleph

0.70

frey

0.68

oing

0.68

heses

0.68

 barking

0.64

 notwithstanding

0.63

xus

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.