INDEX

Explanations

phrases indicating ongoing or repeated actions over time

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

Occurrences within time periods (month/year)

np_acts-logits-general · gemini-2.0-flash

throughout the year

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

UrlResolution

-0.63

 للمعارف

-0.61

 архивлан

-0.60

astéroïdes

-0.60

Географи

-0.57

addContainerGap

-0.54

 Alca

-0.53

 gawas

-0.52

ruzione

-0.51

loped

-0.50

POSITIVE LOGITS

 summer

0.71

reportWebVitals

0.69

 August

0.68

AutoField

0.64

 January

0.63

parametrize

0.63

 October

0.63

 July

0.62

 September

0.62

 December

0.61

Activations Density 0.152%

phrases indicating ongoing or repeated actions over time

Occurrences within time periods (month/year)

throughout the year

No Comments

No Known Activations