INDEX

Explanations

expressions of emotional vulnerability and physical interactions between characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 feroit

-0.75

 auroit

-0.74

berdayakan

-0.73

 defaultstate

-0.71

 ainfi

-0.71

 storici

-0.65

antaranya

-0.65

 mauva

-0.65

 purpoſe

-0.63

 amitié

-0.63

POSITIVE LOGITS

 looked

0.61

 seemed

0.58

msgTypes

0.58

ItemBackground

0.56

MessageTagHelper

0.55

 '\\;'

0.54

seemed

0.53

 Looks

0.52

apparently

0.52

“

0.50

Activations Density 0.125%

expressions of emotional vulnerability and physical interactions between characters

No Comments

No Known Activations