INDEX

Explanations

mathematical notations and symbols

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

<start_of_turn>user affiliations

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

 kaarangay

-0.77

webElementXpaths

-0.61

endphp

-0.59

ніципалі

-0.56

 ivelany

-0.54

 venganza

-0.54

ględ

-0.54

 Jurí

-0.54

ambién

-0.50

 pierna

-0.49

POSITIVE LOGITS

 hail

0.41

 Sapi

0.41

 ['./

0.40

 hails

0.39

indeer

0.38

gi

0.37

tonode

0.37

xlabel

0.36

 ModelExpression

0.36

 custom

0.35

Activations Density 0.015%

mathematical notations and symbols

<start_of_turn>user affiliations

No Comments

No Known Activations