INDEX

Explanations

calls to load or read data in a programmatic context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PerformLayout

-0.80

ngdoc

-0.67

Enciclopedia

-0.62

inergic

-0.57

tlement

-0.56

hObject

-0.52

leyebilirsiniz

-0.51

chartInstance

-0.51

("]");

-0.50

muss

-0.49

POSITIVE LOGITS

ImageContext

0.60

 الدولى

0.59

webElementXpaths

0.55

WithIOException

0.54

sizeCache

0.53

 صوتيه

0.52

itinéraire

0.52

 autorytatywna

0.50

 فريبيس

0.49

enterOuterAlt

0.49

Activations Density 0.379%

calls to load or read data in a programmatic context

No Comments

No Known Activations