INDEX

Explanations

references to numerical values and 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 @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

tvguidetime

-0.77

-0.73

 LoggerFactory

-0.64

XHR

-0.57

(!__

-0.56

ServletException

-0.53

MemoryWarning

-0.52

::_('

-0.51

ConstraintMaker

-0.51

 full

-0.50

POSITIVE LOGITS

CodedInputStream

0.75

 laterales

0.64

 Autorizaciones

0.63

 betweenstory

0.62

مصادر

0.62

 dieux

0.61

 préférence

0.61

 mergeFrom

0.60

 prisonniers

0.59

 manquante

0.59

Activations Density 0.600%

references to numerical values and statistical measures

No Known Activations