INDEX

Explanations

content that simplifies complex concepts for a general audience

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

simple explanations for laymen

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

matchCondition

-0.51

enderror

-0.47

帖最后由

-0.42

 فريبيس

-0.40

tagHelperRunner

-0.40

sniff

-0.39

makeConstraints

-0.35

pieler

-0.34

才有

-0.33

 Nachteile

-0.32

POSITIVE LOGITS

わかり

0.55

Попис

0.55

分かり

0.52

ValueStyle

0.51

icating

0.48

 laymen

0.48

Phaser

0.48

Хьажоргаш

0.47

didSet

0.47

 layman

0.46

Activations Density 0.312%

content that simplifies complex concepts for a general audience

simple explanations for laymen

No Comments

No Known Activations