INDEX

Explanations

elements related to function calls and object properties in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

tvguidetime

-0.90



-0.86

 autorytatywna

-0.74

complexContent

-0.71

 Audiodateien

-0.69

 betweenstory

-0.68

InjectAttribute

-0.67

Parcelize

-0.66

AsUp

-0.66

rungsseite

-0.65

POSITIVE LOGITS

<?=$

0.60

="<?=$

0.55

arv

0.53

 youngest

0.53

|}{$

0.53

NUMX

0.51

IVATE

0.50

!("

0.50

StartCoroutine

0.50

last

0.49

Activations Density 0.173%

elements related to function calls and object properties in code

No Comments

No Known Activations