INDEX

Explanations

concepts related to constraints and creative problem-solving

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

words followed by prepositions

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

ⓧ

-0.52

enderror

-0.47

Suara

-0.47

 חיצוניים

-0.46

 ModelExpression

-0.44

 Vesta

-0.43

 Bolo

-0.43

 rekening

-0.42

Wra

-0.41

➋

-0.41

POSITIVE LOGITS

featureID

0.51

alyptus

0.42

reactstrap

0.41

 banget

0.40

 defaultstate

0.40

writeFieldEnd

0.40

 gethan

0.39

səhifə

0.39

ंदीखरीदारी

0.37

UrlResolution

0.37

Activations Density 0.138%

concepts related to constraints and creative problem-solving

words followed by prepositions

No Comments

No Known Activations