INDEX

Explanations

references to patients and customer service

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

following "patient" or "customer"

np_acts-logits-general · gemini-2.0-flash

patient or customer service

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PerformLayout

-0.73

adpleegd

-0.68

NameInMap

-0.62

 mergeFrom

-0.57

 تضيفلها

-0.57

NOPQRST

-0.56

AnimationsModule

-0.56

 musées

-0.55

 constitución

-0.55

 épis

-0.54

POSITIVE LOGITS

 friendly

0.67

 participation

0.64

 engagement

0.61

 empowerment

0.60

 satisfaction

0.60

 relations

0.60

friendly

0.59

 perception

0.59

 perspectives

0.58

 involvement

0.58

Activations Density 0.429%

references to patients and customer service

following "patient" or "customer"

patient or customer service

No Comments

No Known Activations