INDEX

Explanations

technical references and structures related to data objects in programming contexts

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

code documentation examples

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

aarrggbb

-0.66

Халык

-0.54

 الحره

-0.53

 للاسماء

-0.52

 Photocase

-0.49

/**

-0.48

➯

-0.48

 &___

-0.47

 næste

-0.47

 referenties

-0.45

POSITIVE LOGITS

enderror

0.44

InjectMocks

0.41

acionales

0.37

belong

0.37

BeginContext

0.36

 fusca

0.36

 milik

0.35

 unfairly

0.35

consulté

0.34

catus

0.34

Activations Density 0.084%

technical references and structures related to data objects in programming contexts

code documentation examples

No Comments

No Known Activations