INDEX

Explanations

action words related to effects or changes in various contexts

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

ending in "ing" that relate to cause or effect

np_acts-logits-general · gemini-2.0-flash

factor or effect

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

AsUp

-0.73

 ſein

-0.68

 müſſen

-0.63

 protoimpl

-0.63

ſchaft

-0.63

 censiti

-0.63

extAlignment

-0.63

WaitGroup

-0.62

Portály

-0.61

 laſſen

-0.61

POSITIVE LOGITS

 factor

0.55

 factors

0.51

 effect

0.47

factor

0.41

 agent

0.40

ly

0.38

 agents

0.34

 aspects

0.34

 Factor

0.33

因素

0.31

Activations Density 0.466%

action words related to effects or changes in various contexts

ending in "ing" that relate to cause or effect

factor or effect

No Comments

No Known Activations