INDEX

Explanations

specific formatting or structural elements in programmatic or mathematical contexts

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

__':

-0.87

 Roskov

-0.84

хьтан

-0.81

contentLoaded

-0.81

 ويكيميديا

-0.80

 himo

-0.80

 Italijanski

-0.79

ombia

-0.79

JDK

-0.79

__).

-0.79

POSITIVE LOGITS

itemize

1.24

*-

0.84

0.80

-*

0.76

 Potsdam

0.73

awtextra

0.71

---------------

0.71

/-

0.70

&-

0.70

Activations Density 0.008%

specific formatting or structural elements in programmatic or mathematical contexts

No Comments

No Known Activations