INDEX

Explanations

technical terms and identifiers related to software development environments

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

Code, software, or versions

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

InitVars

-0.42

 informée

-0.41

 IFTT

-0.38

htaccess

-0.37

 FetchType

-0.36

 CascadeType

-0.36

uminense

-0.36

Sơ

-0.35

adaptiveStyles

-0.34

opedia

-0.34

POSITIVE LOGITS

 zijne

0.61

 mijne

0.55

SpringBootTest

0.52

 piuttosto

0.49

SequentialGroup

0.47

 sentimenti

0.46

étoit

0.44

 gynhyrchwyd

0.44

 '-';

0.44

 Normdatei

0.44

Activations Density 0.310%

technical terms and identifiers related to software development environments

Code, software, or versions

No Comments

No Known Activations