INDEX

Explanations

phrases that indicate dependency or variability based on conditions

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

"Depends" followed by "on" or "upon"

np_acts-logits-general · gemini-2.0-flash

depend on or upon

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 Wikimedijinoj

-0.45

KommentareTeilen

-0.44

RTEX

-0.43

parsedMessage

-0.43

</thead>

-0.43

 leaſt

-0.42

tagHelperRunner

-0.41

+#+

-0.41

 الرياضيه

-0.40

 pleaſure

-0.40

POSITIVE LOGITS

 upon

0.65

upon

0.62

 Depend

0.56

Upon

0.56

 Upon

0.54

 UPON

0.52

DEP

0.51

dep

0.49

DEP

0.48

Depend

0.47

Activations Density 0.087%

phrases that indicate dependency or variability based on conditions

"Depends" followed by "on" or "upon"

depend on or upon

No Comments

No Known Activations