INDEX

Explanations

elements related to therapy, mental health, and emotional processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

CORBA

-0.69

ölker

-0.61

setVerticalGroup

-0.58

يميديا

-0.58

 الاطلاع

-0.56

 समीक्षाओं

-0.55

ViewFeatures

-0.54

mány

-0.54

apnews

-0.52

rungsseite

-0.52

POSITIVE LOGITS

 disreg

0.70

 unhelpful

0.67

 reactivity

0.66

 verur

0.59

 dise

0.58

 Shame

0.57

 shame

0.56

WebVitals

0.56

ChildScrollView

0.56

Shame

0.56

Activations Density 0.314%

elements related to therapy, mental health, and emotional processing

No Comments

No Known Activations