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

Not in Any Lists

No Comments

Negative Logits

wana

-0.74

robe

-0.71

luster

-0.71

akov

-0.70

achev

-0.67

etz

-0.66

 Nieto

-0.66

SM

-0.64

packs

-0.63

 Adin

-0.61

POSITIVE LOGITS

ŃĶ

0.70

ife

0.70

alde

0.69

ļéĨĴ

0.68

ality

0.63

HCR

0.63

iframe

0.62

ãĥĨ

0.61

@@@@

0.61

 rendition

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.