INDEX

Explanations

references to darkness and dark imagery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

osoever

-0.91

RenderAtEndOf

-0.72

tyfik

-0.70

mfrac

-0.69

 propOrder

-0.68

katapos

-0.67

országban

-0.64

vra

-0.63

كذا

-0.62

(;;)

-0.60

POSITIVE LOGITS

 DARK

1.58

 Dark

1.56

 dark

1.51

 darkness

1.48

Dark

1.46

DARK

1.46

Darkness

1.39

darkness

1.38

dark

1.37

 Darkness

1.32

Activations Density 0.117%

references to darkness and dark imagery

No Comments

No Known Activations