INDEX

Explanations

specific phrases related to detection and distinguishing characteristics within scientific contexts

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-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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 renta

-0.30

 Pharmaceutical

-0.30

auré

-0.29

 bourgeoisie

-0.29

MouseOver

-0.28

 flori

-0.27

Couleur

-0.27

 doInBackground

-0.27

EventType

-0.26

 influen

-0.26

POSITIVE LOGITS

 nakalista

0.69

 Italijani

0.67

GEBURTSDATUM

0.62

:✨

0.60

 <=",

0.60

 EconPapers

0.60

 مرئيه

0.59

GenerationType

0.59

Referanser

0.59

LookAnd

0.58

Activations Density 0.099%

specific phrases related to detection and distinguishing characteristics within scientific contexts

No Comments

No Known Activations