INDEX

Explanations

structured references, likely related to legislative or legal content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Италијани

-0.74

 виправивши

-0.66

 linkovi

-0.65

verwijspagina

-0.61

ModelBuilder

-0.59

 estimés

-0.58

OGND

-0.57

LLocation

-0.54

 tartalomajánló

-0.54

TypedDataSet

-0.53

POSITIVE LOGITS

eneuve

0.68

GOTREF

0.66

WriteTagHelper

0.63

PositiveButton

0.61

writeFieldEnd

0.57

 AssemblyCulture

0.55

 Offisielt

0.55

rxjs

0.55

 PropTypes

0.54

LAHOMA

0.53

Activations Density 0.368%

structured references, likely related to legislative or legal content

No Comments

No Known Activations