INDEX

Explanations

references to divine concepts or introductory phrases in text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Попис

-0.91

 itſelf

-0.85

 ―――――

-0.84

الدراسه

-0.83

InjectAttribute

-0.82

intenance

-0.82

 Roskov

-0.81

 下午

-0.81

 NDEBUG

-0.80

 cdti

-0.80

POSITIVE LOGITS

how

0.75

Heres

0.69

 what

0.69

 here

0.62

Ecco

0.61

 another

0.61

the

0.59

 heres

0.58

 ecco

0.57

 Вот

0.57

Activations Density 0.113%

references to divine concepts or introductory phrases in text

No Comments

No Known Activations