INDEX

Explanations

references to institutions, particularly in the context of research and funding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.18.hook_mlp_out

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

StructEnd

-0.79

RefNanny

-0.77

Efq

-0.76

 المعيارى

-0.76

 considérons

-0.75

ंदीखरीदारी

-0.73

expandindo

-0.71

 Exacts

-0.71

WaitGroup

-0.71

ItemBackground

-0.69

POSITIVE LOGITS

 expected

0.40

 expects

0.40

 regulator

0.39

外部リンク

0.38

hibernate

0.37

 bước

0.36

丁目

0.36

 expect

0.36

krishna

0.35

zegorz

0.35

Activations Density 0.180%

references to institutions, particularly in the context of research and funding

No Comments

No Known Activations