INDEX

Explanations

references to political or judicial offices and positions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Roskov

-0.65

tagHelperRunner

-0.65

новниш

-0.62

Parcelize

-0.62

<![

-0.58

ayaquil

-0.56

BufferException

-0.56

 strick

-0.55

enchymal

-0.54

 WebDriverWait

-0.53

POSITIVE LOGITS

job

0.79

 duties

0.79

 positions

0.76

 position

0.76

 office

0.74

 jobs

0.73

 respon

0.73

 leadership

0.72

 authority

0.70

 jabatan

0.69

Activations Density 0.536%

references to political or judicial offices and positions

No Comments

No Known Activations