INDEX

Explanations

product or model identifiers, especially in conjunction with specific brands or technical specifications

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

Flex Atlas ACLE II

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

AnchorTagHelper

-0.53

 pouvoit

-0.49

httphttps

-0.47

 Bewußt

-0.45

 kultury

-0.44

رشف

-0.44

angering

-0.43

XmlAccessType

-0.41

Referências

-0.41

GEBURTS

-0.41

POSITIVE LOGITS

 surla

0.49

AndEndTag

0.45

 AttributeSet

0.44

 AppCompatTheme

0.42

 createSlice

0.41

muir

0.39

ByExample

0.39

よいよ

0.39

mentaux

0.37

 securely

0.36

Activations Density 0.016%

product or model identifiers, especially in conjunction with specific brands or technical specifications

Flex Atlas ACLE II

No Comments

No Known Activations