INDEX

Explanations

numerical values and their organization within a dataset

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

Numbers and exponents in mathematical expressions

np_acts-logits-general · gemini-2.0-flash

seven

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

QMetaType

-0.72

 postIndex

-0.60

 doInBackground

-0.59

 الرياضيه

-0.56

 كومونز

-0.55

Personendaten

-0.54

 peroxidase

-0.53

addCriterion

-0.53

opor

-0.52

gable

-0.52

POSITIVE LOGITS

0.83

 seven

0.70

 seventh

0.70

VII

0.65

 tujuh

0.62

 Seven

0.61

 seventy

0.59

 Seventy

0.58

VII

0.58

seven

0.57

Activations Density 0.595%

numerical values and their organization within a dataset

Numbers and exponents in mathematical expressions

seven

No Comments

No Known Activations