INDEX

Explanations

technical terms related to measurements and analysis in scientific contexts

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

Followed by "of," "in," "to," or "as"

np_acts-logits-general · gemini-2.0-flash

phrase completions

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

 ExecuteAsync

-0.71

ANSA

-0.55

Totals

-0.52

].)

-0.52

 fides

-0.51

Ahhh

-0.50

uxxxx

-0.48

 HasFactory

-0.47

 determinations

-0.46

 Exactos

-0.46

POSITIVE LOGITS

 equipments

0.84

 convenable

0.84

 advices

0.81

 evidences

0.77

Ⅱ

0.75

 staffs

0.74

Ⅰ

0.73

 prouve

0.71

 shrimps

0.71

 Besides

0.70

Activations Density 4.834%

technical terms related to measurements and analysis in scientific contexts

Followed by "of," "in," "to," or "as"

phrase completions

No Comments

No Known Activations