INDEX

Explanations

references to coding structures and functionalities

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

property:

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

TypedDataSet

-0.60

GEBURTSDATUM

-0.58

OGND

-0.57

UnusedPrivate

-0.55

 GreatSchools

-0.55

ьаж

-0.53

SequentialGroup

-0.53

UnitTesting

-0.52

最快更新

-0.51

 combineReducers

-0.48

POSITIVE LOGITS

canestro

0.35

 mention

0.34

 atsi

0.33

եց

0.33

ANTAGE

0.32

asis

0.31

 chuva

0.31

plug

0.30

 mentioning

0.30

Em

0.30

Activations Density 0.294%

references to coding structures and functionalities

property:

No Comments

No Known Activations