INDEX

Explanations

terms related to engagement and commitment in relationships

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

engaged, engagement, or broken off

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

RegressionTest

-0.61

AndEndTag

-0.58

Tikang

-0.55

haikusbot

-0.54

UnusedPrivate

-0.54

EndContext

-0.50

UserScript

-0.49

 surla

-0.49

таратура

-0.49



-0.47

POSITIVE LOGITS

 engagement

0.93

 Engagement

0.89

Engagement

0.79

 Engaged

0.77

 engagements

0.73

 betro

0.72

engagement

0.71

 fidanz

0.69

 wedding

0.68

 engaged

0.66

Activations Density 0.010%

terms related to engagement and commitment in relationships

engaged, engagement, or broken off

No Comments

No Known Activations