INDEX

Explanations

references to various policies and their implications in different contexts

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

"policy" or "official"

np_acts-logits-general · gemini-2.0-flash

official policy and strategy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

تقاوى

-0.72

KommentareTeilen

-0.68

batore

-0.63

 NSCoder

-0.61

 ویکی‌پدیا

-0.59

 تضيفلها

-0.58

antastic

-0.54

UseVisualStyle

-0.54

issima

-0.51

ciclopedia

-0.50

POSITIVE LOGITS

 policy

2.26

 policies

2.01

policy

1.92

 Policy

1.86

Policy

1.77

 POLICY

1.71

 strategy

1.71

 Policies

1.69

policies

1.65

POLICY

1.64

Activations Density 0.253%

references to various policies and their implications in different contexts

"policy" or "official"

official policy and strategy

No Comments

No Known Activations