INDEX

Explanations

numerical sequences or mathematical expressions

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

Appears before a date or number

np_acts-logits-general · gemini-2.0-flash

days, months, numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 estekak

-0.79

 himo

-0.66

########.

-0.61

ihr

-0.60

RegressionTest

-0.60

رشف

-0.59

 betweenstory

-0.59

setVerticalGroup

-0.58

faced

-0.56

 otomatig

-0.55

POSITIVE LOGITS

 stanovnika

0.55

 Replaced

0.52

featureID

0.51

culously

0.51

st

0.50

Portale

0.50

iest

0.49

Cous

0.49

 bağlantılar

0.48

AccessorTable

0.48

Activations Density 0.114%

numerical sequences or mathematical expressions

Appears before a date or number

days, months, numbers

No Comments

No Known Activations