INDEX

Explanations

proper nouns, particularly names of individuals involved in various contexts, often in the arts or sciences

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

IndentedString

-0.74

 متعلقه

-0.72

RegressionTest

-0.68

CWE

-0.68

Rhestr

-0.64

IVEREF

-0.64

 ujednoznacz

-0.62

aarrggbb

-0.60

γον

-0.59

存于互联网档案馆

-0.58

POSITIVE LOGITS

DataPropertyName

0.49

 aanwezig

0.49

 réponses

0.48

 decorativos

0.48

 présentés

0.48

 regioni

0.47

 individuale

0.47

 decorativas

0.47

 lettera

0.47

 OnEnable

0.47

Activations Density 0.445%

proper nouns, particularly names of individuals involved in various contexts, often in the arts or sciences

No Comments

No Known Activations