INDEX

Explanations

terms related to grievance processes and compliance policies

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

rules and procedures

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

 незавершена

-0.59

BibitemShut

-0.58

󠁢

-0.58

 nahilalakip

-0.56

bibfield

-0.56

 zuſammen

-0.54

WireFormatLite

-0.54

 Infór

-0.52

:✨

-0.52

 ſeine

-0.52

POSITIVE LOGITS

 policy

0.52

 Policy

0.50

Policy

0.45

 principle

0.40

 policies

0.38

 rule

0.36

 System

0.36

 procedures

0.36

 outlined

0.35

 system

0.35

Activations Density 0.012%

terms related to grievance processes and compliance policies

rules and procedures

No Comments

No Known Activations