INDEX

Explanations

references to individuals or groups of individuals in various 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

ArgsConstructor

-0.83

Idy

-0.81

<<=

-0.80

"]);

-0.79

hysema

-0.78

>\<^

-0.77

TagHelpers

-0.77

ientôt

-0.77

**/

-0.77

()]

-0.77

POSITIVE LOGITS

 Person

1.61

 Persons

1.58

 person

1.56

 PERSON

1.51

person

1.47

Persons

1.45

Person

1.45

 PERSONS

1.40

 persons

1.39

PERSON

1.36

Activations Density 0.052%

references to individuals or groups of individuals in various contexts

No Comments

No Known Activations