INDEX

Explanations

references to operating conditions and parameters in a technical context

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

from followed by specific words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

onViewCreated

-0.72

WebVitals

-0.70

 ſeine

-0.69

 dieſer

-0.68

linawan

-0.68

 ſein

-0.68

ロウィン

-0.68

 ſei

-0.68

niſſe

-0.66

addPreferred

-0.66

POSITIVE LOGITS

ly

0.35

mente

0.34

Parcelize

0.34

化

0.33

 لئے

0.33

 nawr

0.33

atamente

0.32

以上

0.31

化的

0.31

def

0.31

Activations Density 0.272%

references to operating conditions and parameters in a technical context

from followed by specific words

No Comments

No Known Activations