INDEX

Explanations

repeated references to the letter 'G' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.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

ithub

-0.42

fjspx

-0.42

rid

-0.38

dig

-0.35

roup

-0.35

ruppo

-0.35

webElementXpaths

-0.34

allery

-0.33

rungsseite

-0.33

roups

-0.33

POSITIVE LOGITS

oredCriteria

0.58

httphttps

0.55

ंदीखरीदारी

0.53

 مرئيه

0.52

RegistryLite

0.52

 EconPapers

0.50

KommentareTeilen

0.49

Personensuche

0.49

ACHUSET

0.48

Erreferentziak

0.47

Activations Density 0.324%

repeated references to the letter 'G' in various contexts

No Comments

No Known Activations