INDEX

Explanations

programming syntax elements and operators

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

Code-related terms or function names

np_acts-logits-general · gemini-2.0-flash

function names and parameters

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

<eos>

-0.69

the

-0.52

The

-0.45

 […]

-0.43

ReferenceEquals

-0.41

me

-0.41

su

-0.39

 않는

-0.39

Na

-0.39

POSITIVE LOGITS

تقاوى

1.07

verwijspagina

1.04



0.96

 незавершена

0.92

 pinulongan

0.91

homonymie

0.88

存于互联网档案馆

0.88

MigrationBuilder

0.85

RectangleBorder

0.83

 تضيفلها

0.81

Activations Density 0.503%

programming syntax elements and operators

Code-related terms or function names

function names and parameters

No Comments

No Known Activations