INDEX

Explanations

terms related to mathematical definitions and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 للاسماء

-0.77

oredCriteria

-0.69

########.

-0.63

IntoConstraints

-0.59

sizeCache

-0.57

]")]

-0.54



-0.54

⤹

-0.54

UnusedPrivate

-0.53

évaluateur

-0.52

POSITIVE LOGITS

'{@

0.53

 surrounding

0.41

 Anexo

0.40

 adjacent

0.38

XDECREF

0.38

indirect

0.37

 neighbouring

0.36

Vaata

0.36

 Independiente

0.35

adjacent

0.35

Activations Density 1.862%

terms related to mathematical definitions and structures

No Comments

No Known Activations