INDEX

Explanations

mentions related to menu items or selections

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "menu."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

å¥³

-0.76

ioxide

-0.72

esville

-0.71

âĢ¢âĢ¢âĢ¢âĢ¢

-0.69

 Mary

-0.67

UG

-0.63

Coy

-0.61

 Fundamental

-0.61

 Valkyrie

-0.60

Ñĭ

-0.60

POSITIVE LOGITS

 menu

1.08

 menus

1.07

isine

0.99

menu

0.98

 Menu

0.90

entry

0.89

cloth

0.89

 drawer

0.86

eteria

0.84

ropri

0.84

Activations Density 0.007%

mentions related to menu items or selections

occurrences of the word "menu."

No Comments

No Known Activations