INDEX

Explanations

terms related to punishment and punitive actions

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

punishment and penalties

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

 initComponents

-0.48

+#+

-0.45

 hijas

-0.38

 simplifié

-0.38

 building

-0.38

viewWillAppear

-0.38

 Gelegenheit

-0.38

Ever

-0.38

 fatos

-0.38

 rencont

-0.37

POSITIVE LOGITS

 punishment

1.29

 Punishment

1.23

 punish

1.23

 penalty

1.11

 penalties

1.09

 punishments

1.08

 Penalty

1.07

 punished

1.06

Penalty

1.05

 Penalties

1.04

Activations Density 0.041%

terms related to punishment and punitive actions

punishment and penalties

No Comments

No Known Activations

terms related to punishment and punitive actions

punishment and penalties

No Comments

No Known Activations