INDEX

Explanations

references to settings and preferences in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

]<<"

-0.88

 isolada

-0.85

 AssemblyProduct

-0.84

 RemoteException

-0.82

 CreateTagHelper

-0.81

 virtuales

-0.79

ExecuteReader

-0.78

 beroep

-0.77

 camiones

-0.76

 оригіналу

-0.76

POSITIVE LOGITS

Settings

1.49

 settings

1.37

 Settings

1.37

settings

1.27

 SETTINGS

1.15

getSettings

1.08

SETTINGS

1.06

 SETTING

0.95

AppSettings

0.94

 setting

0.94

Activations Density 0.077%

references to settings and preferences in a technical context

No Comments

No Known Activations