INDEX

Explanations

phrases and words expressing legal or ethical dilemmas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

localctx

-0.53

 eccell

-0.52

 مشين

-0.50

PreInfinity

-0.50

 للمعارف

-0.50

gridy

-0.47

 doInBackground

-0.46

ngdoc

-0.45

 thermoc

-0.45

ผ่าน

-0.44

POSITIVE LOGITS

 AssemblyCulture

0.62

Datuak

0.58

 setTotal

0.57

rungsseite

0.57

思わず

0.55

SwitchCompat

0.55

Personensuche

0.55

::$_

0.53

kig

0.52

bnf

0.52

Activations Density 0.175%

phrases and words expressing legal or ethical dilemmas

No Comments

No Known Activations