INDEX

Explanations

code snippets that check if an index is equivalent to -1 and/or whether a specific CSS value doesn't exist

oai_token-act-pair · gemini-2.0-flash

Code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Audiodateien

-0.63

ContentAsync

-0.62

 CreateTagHelper

-0.61

phazard

-0.60

esModule

-0.59

RequestMapping

-0.58

Carcinogenicity

-0.57

########.

-0.56

fromnode

-0.55

 Parenthood

-0.54

POSITIVE LOGITS

(-

0.79

(-

0.70

$(-

0.62

==-

0.60

=-

0.60

$-

0.59

=-

0.54

$(-

0.54

,-

0.54

Activations Density 1.755%

code snippets that check if an index is equivalent to -1 and/or whether a specific CSS value doesn't exist

Code

No Comments

No Known Activations

code snippets that check if an index is equivalent to -1 and/or whether a specific CSS value doesn't exist

Code

No Comments

No Known Activations