INDEX

Explanations

terms and concepts related to technical investigation and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

atur

-0.47

https

-0.44

[*]

-0.43

 Čes

-0.42

Segoe

-0.42

NFA

-0.41

Afterwards

-0.41

 https

-0.41

'/',

-0.41

振

-0.41

POSITIVE LOGITS

contentLoaded

0.94

GEBURTSDATUM

0.91

 &___

0.87

Personendaten

0.84

 Partagez

0.83

SharedCtor

0.81

出版年

0.78

MethodManager

0.74

RegistryLite

0.73

Activations Density 0.956%

terms and concepts related to technical investigation and analysis

No Comments

No Known Activations