INDEX

Explanations

phrases that express emotional states or personal reflections

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

processes or actions

np_acts-logits-general · gemini-2.0-flash

predicting next words in phrases

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Климат

-0.55

 hız

-0.52

Ỉ

-0.50

sivu

-0.48

 Relations

-0.47

 Ablauf

-0.46

خة

-0.45

Fazit

-0.45

frain

-0.45

'][]

-0.44

POSITIVE LOGITS

SequentialGroup

0.79



0.79

 الاطلاع

0.72

ViewFeatures

0.72

AnimationsModule

0.72

]")]

0.72

 tartalomajánló

0.70

TemporalType

0.70

 насељу

0.68

 ujednoznacz

0.68

Activations Density 0.433%

phrases that express emotional states or personal reflections

processes or actions

predicting next words in phrases

No Comments

No Known Activations