INDEX

Explanations

references to points and scoring in competitive 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 @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 czeka

-0.33

 Fests

-0.33

rü

-0.32

 Schnell

-0.31

 خل

-0.31

je

-0.31

 resourceCulture

-0.30

 amazing

-0.30

 interesting

-0.30

 Glas

-0.29

POSITIVE LOGITS

RegressionTest

0.69

 noDo

0.68

Diweddarwch

0.59

angliski

0.55

 ſind

0.54

 الاطلاع

0.53

queryInterface

0.52

exitRule

0.52

webElement

0.51

noid

0.51

Activations Density 0.139%

references to points and scoring in competitive contexts

No Comments

No Known Activations