INDEX

Explanations

connections and relationships between concepts or entities

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 produzir

-0.35

 Freizeit

-0.33

 Roskov

-0.33

hydro

-0.32

 prétend

-0.32

Sol

-0.32

 konge

-0.32

 ää

-0.31

 cervello

-0.31

ciptakan

-0.30

POSITIVE LOGITS

twimg

0.73

الحياه

0.59

UnitTesting

0.56

 дописавши

0.51

ArgumentParser

0.49

BITDA

0.48

parsedMessage

0.48

bibfield

0.47

URLException

0.47

ंदीखरीदारी

0.47

Activations Density 0.996%

connections and relationships between concepts or entities

No Comments

No Known Activations