INDEX

Explanations

indicators of programming and output statements

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

references to structured data formats, especially JSON

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

In, Out, Output

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AsUp

-0.73

 nahilalakip

-0.60

protoimpl

-0.58

 SqlParameter

-0.56

 SqlConnection

-0.55

PathParam

-0.54

قایناق‌لار

-0.53

 Réponses

-0.53

ждую

-0.52

 jdbcTemplate

-0.51

POSITIVE LOGITS

[]:

0.86

Datuak

0.63

 상세

0.55

 nakalista

0.54

OwnProperty

0.52

<tbody>

0.52

 bezeichneter

0.52

</tr>

0.50

MLLoader

0.49

 surla

0.49

Activations Density 0.004%

indicators of programming and output statements

references to structured data formats, especially JSON

In, Out, Output

No Comments

No Known Activations