INDEX

Explanations

references to specific terms or variables within a scientific or technical context

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

Followed by "in" or "terms" (math context)

np_acts-logits-general · gemini-2.0-flash

terms in

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

GEBURTSDATUM

-0.69

 disambiguazione

-0.60

 kwenye

-0.58

 protoimpl

-0.57

scriptcase

-0.57

WriteBarrier

-0.56

TypedDataSet

-0.56

Życiorys

-0.55

homonymie

-0.53

λω

-0.53

POSITIVE LOGITS

in

1.48

in

1.45

In

1.20

In

1.12

getIn

0.89

인

0.79

IN

0.77

 inquest

0.76

в

0.69

ใน

0.64

Activations Density 0.145%

references to specific terms or variables within a scientific or technical context

Followed by "in" or "terms" (math context)

terms in

No Comments

No Known Activations