INDEX

Explanations

email addresses and names associated with them

oai_token-act-pair · gemini-2.0-flash

parentheses and brackets

np_token-act-pair-logits · gpt-4o-mini

say "@"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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

ScopeManager

-0.84

migrationBuilder

-0.73

SourceChecksum

-0.65

WebElementEntity

-0.64

InstrumentedTest

-0.63

EndGlobalSection

-0.62

ⓧ

-0.60

")));

-0.59

HasAnnotation

-0.58

IsContent

-0.58

POSITIVE LOGITS

0.85

（

0.71

0.63

(.

0.56

 Abingdon

0.56

(“

0.54

((

0.53

(.

0.53

 SafeMath

0.51

$($

0.50

Activations Density 1.672%

email addresses and names associated with them

parentheses and brackets

say "@"

No Comments

No Known Activations