INDEX

Explanations

technical jargon and terminology related to coding and programming contexts

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

build my own IP headers

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

 GenerationType

-0.52

 zoeken

-0.51

 voelen

-0.49

onymes

-0.48

écu

-0.48

 geluid

-0.47

 plumas

-0.47

 vertellen

-0.47

CastException

-0.46

quele

-0.46

POSITIVE LOGITS

 tartalomajánló

0.48

Autoritní

0.40

 pinulongan

0.39

PageIndex

0.37

 Мексичка

0.37

')],

0.36

equ

0.34

舺

0.34

Sta

0.34

')]

0.33

Activations Density 0.123%

technical jargon and terminology related to coding and programming contexts

build my own IP headers

No Comments

No Known Activations