INDEX

Explanations

references to numeric data, particularly in relation to health or statistical measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 must

-1.43

must

-1.26

 Must

-1.11

Must

-1.11

 harus

-0.99

 måste

-0.93

 gotta

-0.93

 MUST

-0.91

 phải

-0.91

MUST

-0.90

POSITIVE LOGITS

AnchorStyles

0.95

TestingModule

0.93

MemoryWarning

0.83

queryInterface

0.80



0.78

 المعيارى

0.78

AxisAlignment

0.78

клопе

0.78

verwijspagina

0.77

routeProvider

0.77

Activations Density 0.886%

references to numeric data, particularly in relation to health or statistical measures

No Comments

No Known Activations