INDEX

Explanations

specific terms related to policies and governance

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

"policy"

np_acts-logits-general · gemini-2.0-flash

policy target, totaling, certainty, matters

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

具备

-0.44

 incontour

-0.41

 Jérusalem

-0.41

 rzeczyw

-0.40

 kapturem

-0.40

Jetzt

-0.39

 chrétien

-0.39

What

-0.39

 colorido

-0.39

 mystérie

-0.38

POSITIVE LOGITS

 policy

2.28

 POLICY

2.13

 Policy

2.13

policy

2.11

Policy

2.05

 policies

1.91

POLICY

1.87

 Policies

1.82

Policies

1.73

 POLICIES

1.65

Activations Density 0.068%

specific terms related to policies and governance

"policy"

policy target, totaling, certainty, matters

No Comments

No Known Activations