INDEX

Explanations

conversational phrases and references to experiences involving self-reflection and personal opinions

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

duration or continuation

np_acts-logits-general · gemini-2.0-flash

throughout or entire time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ExecuteAsync

-0.83

 nahilalakip

-0.75

 CreateTagHelper

-0.74

 snippetHide

-0.73

tvguidetime

-0.72

 Normdatei

-0.70

protoimpl

-0.68

astéroïdes

-0.68

])));

-0.67

"];

-0.66

POSITIVE LOGITS

 throughout

2.57

throughout

2.31

 Throughout

2.17

Throughout

2.05

 entire

1.87

 whole

1.71

whole

1.55

 THRO

1.55

 sepanjang

1.54

 suốt

1.54

Activations Density 0.767%

conversational phrases and references to experiences involving self-reflection and personal opinions

duration or continuation

throughout or entire time

No Comments

No Known Activations