INDEX

Explanations

proper nouns and names of people and places

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

after numbers

np_acts-logits-general · gemini-2.0-flash

alternative or subsequent

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 XNUMX

-0.84

 ་་

-0.82

 doubtnut

-0.81

^(@)

-0.80

 ſind

-0.79

Efq

-0.74

</caption>

-0.73

 itſelf

-0.73

DeleteBehavior

-0.72

 ―――――

-0.71

POSITIVE LOGITS

or

0.78

 also

0.77

 instead

0.73

 invece

0.70

 тоже

0.69

 hingegen

0.67

also

0.65

 ebenfalls

0.61

0.60

 another

0.59

Activations Density 1.031%

proper nouns and names of people and places

after numbers

alternative or subsequent

No Comments

No Known Activations