INDEX

Explanations

indicators of emotional reactions and interpersonal interactions

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

Gestures and nonverbal communication

np_acts-logits-general · gemini-2.0-flash

signaling agreement or understanding

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

 Soccerway

-0.54

 Réponses

-0.50

 onPostExecute

-0.49

 objective

-0.48

Objective

-0.48

canestro

-0.48

 breathing

-0.47

HRC

-0.46

 Objective

-0.46

 allAfrica

-0.46

POSITIVE LOGITS

 signaling

0.88

 signalling

0.79

 Signaling

0.74

 indicating

0.71

sign

0.69

Sign

0.67

 signify

0.66

 semn

0.65

 SIGNAL

0.64

 señal

0.64

Activations Density 0.096%

indicators of emotional reactions and interpersonal interactions

Gestures and nonverbal communication

signaling agreement or understanding

No Comments

No Known Activations