INDEX

Explanations

references to data fields in a structured format, particularly in a programming or data model context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 textStatus

-0.57

 affective

-0.48

kitan

-0.48

 мяса

-0.47

turno

-0.47

Ant

-0.46

HttpException

-0.46

pem

-0.46

 âgées

-0.46

 espar

-0.46

POSITIVE LOGITS

InjectAttribute

0.77

GEBURTSDATUM

0.73

 rows

0.72

AnchorStyles

0.72

matchCondition

0.70

 isolado

0.68

migrationBuilder

0.68

 CascadeType

0.67

MemoryWarning

0.67

 Rows

0.66

Activations Density 0.120%

references to data fields in a structured format, particularly in a programming or data model context

No Comments

No Known Activations