INDEX

Explanations

specific references to names and titles in academic or literary works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

Personensuche

-0.71

tagHelperRunner

-0.68

ंदीखरीदारी

-0.68

+#+#

-0.66

 insuffisamment

-0.64

 <>",

-0.63

 Einfluß

-0.59

 nahilalakip

-0.54

 Signalez

-0.54

toHave

-0.52

POSITIVE LOGITS

LC

0.49

LM

0.44

LQ

0.43

LO

0.41

LT

0.40

LCS

0.39

Lc

0.39

0.38

Lo

0.37

LA

0.37

Activations Density 0.795%

specific references to names and titles in academic or literary works

No Comments

No Known Activations