INDEX

Explanations

proper nouns and associated terms, often names of people or places and sometimes related contextual terms

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ēju

-0.61

//};

-0.50

ต์

-0.46

 refueling

-0.46

enterOuterAlt

-0.45

 Afterwards

-0.45

consts

-0.45

 emporter

-0.44

eniendo

-0.44

剃

-0.44

POSITIVE LOGITS

tagHelperRunner

0.87

 Infórmanos

0.74

MigrationBuilder

0.69

 שוליים

0.68

tanleria

0.66

openzeppelin

0.66

BeginInit

0.61

reportWebVitals

0.61

发表于

0.60

ⓧ

0.60

Activations Density 1.296%

proper nouns and associated terms, often names of people or places and sometimes related contextual terms

No Comments

No Known Activations