INDEX

Explanations

code snippets that perform array manipulations and filtering

oai_token-act-pair · gemini-2.0-flash

Identifying duplicate entries

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تل

-0.46

ha

-0.41

datagrid

-0.40

hwa

-0.39

caid

-0.37

bcryptjs

-0.37

belongsTo

-0.36

ha

-0.36

рано

-0.35

发表于

-0.35

POSITIVE LOGITS

 duplicate

1.80

 duplicates

1.70

 duplicated

1.67

 duplication

1.57

 Duplicate

1.56

duplicate

1.53

dup

1.48

 repeats

1.47

 repeat

1.47

 repetition

1.45

Activations Density 3.268%

code snippets that perform array manipulations and filtering

Identifying duplicate entries

No Comments

No Known Activations