INDEX

Explanations

technical jargon related to circuitry and electronic components

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

•Helix list

No Comments

Negative Logits

+#+#

-0.73

 <=",

-0.68

Geplaatst

-0.65

ngdoc

-0.65

 propOrder

-0.64

Autoritní

-0.62

 كومونز

-0.62

AutoresizingMask

-0.58

 otomatig

-0.56

__":

-0.54

POSITIVE LOGITS

Sharper

0.52

WebVitals

0.52

 itself

0.51

 Malk

0.49

issippi

0.49

ẻo

0.47

ásticos

0.47

 Itself

0.47

enc

0.46

+:+

0.46

Activations Density 1.904%

technical jargon related to circuitry and electronic components

No Comments

No Known Activations