INDEX

Explanations

adjectives indicating quality or effectiveness

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

<start_of_turn> user

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

 lenker

-0.55

 disambiguazione

-0.52

Дереккөздер

-0.51

maty

-0.49

сылкі

-0.48

 güç

-0.44

 cuáles

-0.44

 rajut

-0.44

 Planung

-0.44

 ligiloj

-0.44

POSITIVE LOGITS

✭✭

0.54

 autorytatywna

0.48

 noDo

0.46

 становника

0.46

 invokingState

0.46

 <=",

0.43

 الحره

0.43

:✨

0.42

 ✭✭

0.40

UnusedPrivate

0.40

Activations Density 0.000%

adjectives indicating quality or effectiveness

<start_of_turn> user

No Comments

No Known Activations