INDEX

Explanations

elements related to personal sharing and emotional expression

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

 المعيارى

-0.95

 ―――――

-0.84

InjectAttribute

-0.83

 NDEBUG

-0.83

 незавершена

-0.82

UserScript

-0.80

 forState

-0.79

 protoimpl

-0.79

 ་་

-0.79

 itſelf

-0.78

POSITIVE LOGITS

0.90

0.82

0.80

0.70

...

0.64

0.63

0.60

0.58

↵

0.57

Activations Density 0.054%

elements related to personal sharing and emotional expression

No Comments

No Known Activations