INDEX

Explanations

terms related to inserting data or elements into structures

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 חיצוניים

-0.85

AsUp

-0.76

rativa

-0.74

valueOf

-0.71

"@/

-0.70

[:,

-0.69

ThemeOverlay

-0.68

 bArr

-0.67

wpdb

-0.67

flexDirection

-0.66

POSITIVE LOGITS

 insert

1.66

 inserts

1.66

 Insert

1.65

 Inserts

1.60

 insertion

1.52

 inserted

1.52

Insert

1.50

 Insertion

1.48

 INSERT

1.41

 inserting

1.39

Activations Density 0.015%

terms related to inserting data or elements into structures

No Comments

No Known Activations