INDEX

Explanations

technical terms, particularly those related to programming and system errors

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

featureID

-0.62

<bos>

-0.57

 nakalista

-0.54

 newBuilder

-0.54

Портали

-0.54

قایناق‌لار

-0.53

 VIDEOTAPE

-0.52

 kaarangay

-0.52

 мәкал

-0.51

stretchr

-0.50

POSITIVE LOGITS

RectangleBorder

0.70

stridium

0.60

WebpackPlugin

0.55

TargetException

0.51

flé

0.49

 Cronin

0.47

Hentet

0.47

IBarButtonItem

0.47

AndPassword

0.46

 otomatig

0.45

Activations Density 1.105%

technical terms, particularly those related to programming and system errors

No Comments

No Known Activations