INDEX

Explanations

time-related phrases or indicators

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

following "after" or "of"

np_acts-logits-general · gemini-2.0-flash

time intervals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ynia

-0.37

ánicas

-0.36

balleur

-0.36

ToServer

-0.35

heute

-0.34

 undist

-0.34

denkmal

-0.34

multicolumn

-0.33

brigens

-0.33

 sesuatu

-0.32

POSITIVE LOGITS

TypedDataSet

0.70

 autorytatywna

0.65

новништво

0.60

 հղումներ

0.56

 ligiloj

0.49

Bakgrunnsstoff

0.48

 دیکھیے

0.47

 HttpNotFound

0.47

jspb

0.46

LEGGI

0.46

Activations Density 0.265%

time-related phrases or indicators

following "after" or "of"

time intervals

No Comments

No Known Activations