INDEX

Explanations

terms related to chronic inflammation and treatment dosage levels

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

Adverbs ending in "-ly" modifying verbs

np_acts-logits-general · gemini-2.0-flash

adverb describing impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

EditorBrowsable

-0.47

 الاص

-0.44

aternary

-0.44

 bagay

-0.44

 الأص

-0.44

nischer

-0.44

related

-0.43

vivid

-0.43

 شخص

-0.42

limiting

-0.42

POSITIVE LOGITS

 initComponents

0.93

RectangleBorder

0.82

styleable

0.81

aarrggbb

0.79

 nakalista

0.75

WebServlet

0.73

InputBorder

0.71

 Roskov

0.71

ftagPool

0.69

 Allociné

0.69

Activations Density 0.495%

terms related to chronic inflammation and treatment dosage levels

Adverbs ending in "-ly" modifying verbs

adverb describing impact

No Comments

No Known Activations