INDEX

Explanations

phrases indicating research proposals and future studies

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

preposition followed by verb or noun

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

Первый

-0.30

sī

-0.30

://

-0.30

 purposefully

-0.29

dak

-0.29

ốn

-0.28

Unless

-0.28

 guilt

-0.28

 prejudice

-0.28

webElement

-0.28

POSITIVE LOGITS

 صوتيه

0.75

+#+#

0.73

 للاسماء

0.71

DoubleQuotes

0.69

 AssemblyTitle

0.68

 Signalez

0.66

tonode

0.65

FunctionFlags

0.62

StructEnd

0.61

EndInit

0.60

Activations Density 0.032%

phrases indicating research proposals and future studies

preposition followed by verb or noun

No Comments

No Known Activations