INDEX

Explanations

mathematical symbols and expressions related to inequalities and conditions

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

Enumerations or indexed items

np_acts-logits-general · gemini-2.0-flash

sequences of indices and ranges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

>=

-0.47

⎜

-0.41

>=

-0.41

archiviato

-0.40

qui

-0.37

)>=

-0.36

Jîn

-0.35

Wyd

-0.35

argout

-0.34

}{*}{}

-0.34

POSITIVE LOGITS

uxxxx

0.68

awakeFromNib

0.56



0.55

AndEndTag

0.50

principalTable

0.50

usercontent

0.49

AxisAlignment

0.48

省市镇

0.48

endcsname

0.48

rizona

0.47

Activations Density 0.512%

mathematical symbols and expressions related to inequalities and conditions

Enumerations or indexed items

sequences of indices and ranges

No Comments

No Known Activations