INDEX

Explanations

Japanese names of artists or creators

oai_token-act-pair · gpt-3.5-turbo

names of creators and contributors in relation to a specific project or medium

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Colorado

-0.91

 Colorado

-0.78

pes

-0.70

cro

-0.69

aneers

-0.69

vantage

-0.68

 cocaine

-0.68

 Pyth

-0.67

olitics

-0.67

fec

-0.67

POSITIVE LOGITS

 Tsuk

1.33

ichi

1.22

 Yosh

1.21

ji

1.14

 Akira

1.12

 Yamato

1.09

 Kuro

1.09

jin

1.06

 Shib

1.06

 Shogun

1.05

Activations Density 0.147%

Japanese names of artists or creators

names of creators and contributors in relation to a specific project or medium

No Comments

No Known Activations