INDEX

Explanations

programming terms related to software architecture and framework components

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

programming language keywords

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

HttpFoundation

-0.37

-0.36

 omge

-0.33

 świad

-0.33

ally

-0.33

mittags

-0.33

Synonymes

-0.32

 Estable

-0.32

 amazing

-0.32

 duquel

-0.31

POSITIVE LOGITS

expandindo

1.16

UserScript

0.91

WebVitals

0.86

 createSlice

0.85

oredCriteria

0.84

 ujednoznacz

0.80

 resourceCulture

0.77

SourceChecksum

0.74

 surla

0.73

StoryboardSegue

0.71

Activations Density 0.005%

programming terms related to software architecture and framework components

programming language keywords

No Comments

No Known Activations