INDEX

Explanations

numerical values or references

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

locations, addresses, universities

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

 <<<<<<<<<<<<<<

-0.56

 вікісторінку

-0.45

ngdoc

-0.45

 يتيمه

-0.44

 للاسماء

-0.43

}{*}{}

-0.42

fully

-0.40

 članak

-0.39

ally

-0.39

ObjectModel

-0.39

POSITIVE LOGITS

 marquées

0.48

 downtown

0.44

WriteTagHelper

0.44

 suburb

0.42

 suburbs

0.41

 disponibilités

0.41

ByExample

0.40

 ainfi

0.40

 Betrag

0.39

 stanga

0.39

Activations Density 0.002%

numerical values or references

locations, addresses, universities

No Comments

No Known Activations