INDEX

Explanations

code-related terminology and structure, particularly in programming and library management contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

исленность

-0.37

代

-0.36

 oignon

-0.35

 căr

-0.34

gande

-0.34

 eras

-0.34

 standen

-0.33

 cebola

-0.33

inoma

-0.33

matchCondition

-0.32

POSITIVE LOGITS

 الرياضيه

0.55

oa̍t

0.50

webElementXpaths

0.48

 invokingState

0.48

contentLoaded

0.46

PARATUS

0.45

harusnya

0.44

 Мексичка

0.44

 Throwable

0.43

 Numerade

0.43

Activations Density 0.632%

code-related terminology and structure, particularly in programming and library management contexts

No Comments

No Known Activations