INDEX

Explanations

names and mentions of individuals named "Franc" or "Franç"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Franc" and its variations

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

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

Discussion

-0.75

BOX

-0.71

aeda

-0.69

è¦ļéĨĴ

-0.68

 Hussain

-0.67

PLIED

-0.65

 Anchorage

-0.65

APE

-0.65

puff

-0.64

 Nevada

-0.64

POSITIVE LOGITS

ophone

1.24

isc

0.95

ophile

0.93

 Franc

0.89

shire

0.89

isco

0.88

ais

0.88

atical

0.87

clair

0.86

fri

0.85

Activations Density 0.003%

names and mentions of individuals named "Franc" or "Franç"

references to the name "Franc" and its variations

No Comments

No Known Activations