INDEX

Explanations

language associated with statistical meta-analysis

oai_token-act-pair · gemini-2.0-flash

tokens beginning with 'ma' or 'un'

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

percent

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

 nakalista

-0.90

WebElementEntity

-0.89

 Roskov

-0.86

SourceChecksum

-0.84

Efq

-0.81

 ſeveral

-0.77

FieldBuilder

-0.77

endphp

-0.77

 الحره

-0.76

fjspx

-0.76

POSITIVE LOGITS

ma

0.42

un

0.39

0.37

tapan

0.36

unc

0.36

MAI

0.35

oboda

0.35

mun

0.35

ma

0.35

Activations Density 3.000%

language associated with statistical meta-analysis

tokens beginning with 'ma' or 'un'

percent

No Comments

No Known Activations