INDEX

Explanations

references to categories, identifiers, and system values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

NUMX

-0.72

awaiter

-0.61

 useAppContext

-0.61

PRNewswire

-0.58

достатки

-0.56

]";

-0.55

 scienza

-0.55

 мәкал

-0.55

tekend

-0.54

webElementXpaths

-0.54

POSITIVE LOGITS

 GenerationType

0.63

$_['

0.54

NetworkInfo

0.52

URIComponent

0.48

 FontWeight

0.47

 xmlns

0.47

ghs

0.45

 numberOfRows

0.45

 виправивши

0.44

less

0.44

Activations Density 1.253%

references to categories, identifiers, and system values

No Comments

No Known Activations