INDEX

Explanations

programming and function-related terminology

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

 مشين

-0.54

AccessorTable

-0.54

RenderAtEndOf

-0.47

angliski

-0.38

Autoritní

-0.38

 Suiza

-0.37

hyrchwyd

-0.37

 industriels

-0.37

 utafitiHapana

-0.36

 betekenis

-0.35

POSITIVE LOGITS

SPATH

0.85

OCCURRED

0.54

twimg

0.54

 Akismet

0.53

wpdb

0.49

webElementXpaths

0.47

EFIAPI

0.47

endphp

0.46

addCriterion

0.46

ImageContext

0.44

Activations Density 0.274%

programming and function-related terminology

No Comments

No Known Activations