INDEX

Explanations

names of individuals and their titles or professions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

المراجع

-0.61

مراجع

-0.57

 probability

-0.56

帮

-0.53

achu

-0.52

 aufzu

-0.51

 numberWith

-0.51

partic

-0.49

maar

-0.49

 chal

-0.49

POSITIVE LOGITS

uxxxx

0.59

Personendaten

0.53

Ƚ

0.52

 Traducción

0.48

multer

0.47

 Exacts

0.46

 ["",

0.45

وفاته

0.45

EnableWeb

0.44

udesta

0.44

Activations Density 0.081%

names of individuals and their titles or professions

No Comments

No Known Activations