INDEX

Explanations

numerical values, specifically related to monetary amounts and associated data

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

years, dates, or counts

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

tagHelperRunner

-0.70

rrggbb

-0.66

httphttps

-0.64

новништво

-0.53

 InputDecoration

-0.51

 CreateTagHelper

-0.49

RTLI

-0.48

󠁢

-0.47

IVEREF

-0.47

mergeFrom

-0.47

POSITIVE LOGITS

slip

0.37

 Slip

0.35

vac

0.35

 foie

0.35

vær

0.34

Slip

0.34

diyah

0.33

 Probl

0.32

fortawesome

0.31

MOM

0.31

Activations Density 0.082%

numerical values, specifically related to monetary amounts and associated data

years, dates, or counts

No Comments

No Known Activations