INDEX

Explanations

code segments and library annotations within programming contexts

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

JpaRepository

-0.76

put

-0.59

LiveData

-0.58

setVerticalGroup

-0.56

WaitGroup

-0.56

-0.54

sendStatus

-0.53

OpenHelper

-0.52

hbase

-0.51

us

-0.50

POSITIVE LOGITS

 Савезне

0.93

 Paglinawan

0.78

Personensuche

0.77

تقاوى

0.73

 nahilalakip

0.72

 Roskov

0.68

GEBURTSDATUM

0.68

UnsafeEnabled

0.68

.}(

0.63

'])

0.61

Activations Density 0.054%

code segments and library annotations within programming contexts

No Comments

No Known Activations