INDEX

Explanations

terms related to health, environmental issues, and socio-economic problems

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

"Some" followed by a noun

np_acts-logits-general · gemini-2.0-flash

some or certain

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyProduct

-0.70

NameValuePair

-0.63

AndEndTag

-0.54

gdx

-0.53

]")]

-0.53

يميديا

-0.49

Efq

-0.49

closePath

-0.49

IsContent

-0.47

一共

-0.47

POSITIVE LOGITS

 some

2.70

 certains

2.64

 algunos

2.50

 certaines

2.46

 некоторых

2.40

 некоторые

2.38

 algunas

2.38

 niektórych

2.37

 sommige

2.35

 certain

2.31

Activations Density 1.060%

terms related to health, environmental issues, and socio-economic problems

"Some" followed by a noun

some or certain

No Comments

No Known Activations