INDEX

Explanations

specifications related to layout and design attributes in a coding context

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

user input

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

 EconPapers

-0.64

 feroit

-0.63

 avoient

-0.62

transQ

-0.58

 étoit

-0.57

 indígen

-0.56

 étoient

-0.56

aş

-0.50

 ſever

-0.50

 vôtre

-0.50

POSITIVE LOGITS

 AssemblyCulture

0.44

windowFixed

0.38

Atsauces

0.37

Дереккөздер

0.35

complexContent

0.34

 Италијани

0.33

ClientSize

0.33

حوالہ

0.32

CHAFT

0.32

imageshack

0.32

Activations Density 0.028%

specifications related to layout and design attributes in a coding context

user input

No Comments

No Known Activations