INDEX

Explanations

lists or references to categories and topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Monfieur

-0.73

 myſelf

-0.66

Erreferentziak

-0.63

Personendaten

-0.62

 виправивши

-0.61

HtmlAttribute

-0.60

责任编辑

-0.60

ItemBackground

-0.60

 Universidades

-0.59

 CreateTagHelper

-0.58

POSITIVE LOGITS

expandindo

0.56

rawDesc

0.55

juvant

0.54

verwijspagina

0.52

Portail

0.49

esgue

0.48

ffie

0.47

rativa

0.45

SpringBootTest

0.45

mls

0.45

Activations Density 0.231%

lists or references to categories and topics

No Comments

No Known Activations