INDEX

Explanations

proper nouns, especially names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

oa̍t

-0.61

 مشين

-0.55

 vulgaires

-0.48

γραφία

-0.48

 anteriormente

-0.47

 dezelve

-0.47

rdı

-0.47

kusen

-0.46

Dancer

-0.46

 Unidas

-0.45

POSITIVE LOGITS

Hozzáférés

0.73

 EconPapers

0.71

esModule

0.63

devamını

0.63

$_['

0.61

addPreferredGap

0.57

IContainer

0.57

islav

0.57

 ...,

0.57

AutoField

0.56

Activations Density 0.271%

proper nouns, especially names of individuals

No Comments

No Known Activations