INDEX

Explanations

terms related to data structures and programming concepts

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

Policy schedule identifiers

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

awtextra

-0.66

最快更新

-0.44

ьажоргаш

-0.41

@"/

-0.40

definecolor

-0.40

]=>

-0.39

 мәкал

-0.39

OrBuilder

-0.38

rungsseite

-0.38

DBNull

-0.38

POSITIVE LOGITS

WireFormatLite

0.61

 AssemblyCompany

0.56

TokenNameLBRACE

0.52

حوالہ

0.51

ohistochemistry

0.49

Fleur

0.47

 Gymnasium

0.47

 Stewardship

0.47

льевич

0.47

Portail

0.46

Activations Density 0.101%

terms related to data structures and programming concepts

Policy schedule identifiers

No Comments

No Known Activations