INDEX

Explanations

mention of individuals and names related to 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 @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

UserScript

-0.55

 NSCoder

-0.45

VYMaps

-0.45

XmlAccessType

-0.45



-0.45

 Chwiliwch

-0.44

XmlEnum

-0.44

 espec

-0.44

Schweiz

-0.43

 nakalista

-0.43

POSITIVE LOGITS

gaon

0.59

riwal

0.58

arwal

0.57

ariya

0.57

lesh

0.53

arpur

0.53

wani

0.53

wal

0.51

aliya

0.49

ikar

0.48

Activations Density 0.147%

mention of individuals and names related to various contexts

No Comments

No Known Activations