INDEX

Explanations

expressions of emotional pain and tears

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Tikang

-0.98

+#+#

-0.93

 Roskov

-0.66

 NUKAT

-0.65

verwijspagina

-0.64

protoimpl

-0.64

 simplifié

-0.62

 nahilalakip

-0.61

ereich

-0.61

曖昧さ回避

-0.61

POSITIVE LOGITS

 tears

2.42

 Tears

1.97

tears

1.95

Tears

1.91

 tear

1.77

 wept

1.69

 crying

1.57

 weeping

1.56

 sobbing

1.51

 sobbed

1.49

Activations Density 0.118%

expressions of emotional pain and tears

No Comments

No Known Activations