INDEX

Explanations

technical language and formatting related to mathematical notation

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

Cyfarwyddwr

-0.60

makeText

-0.54

 typelib

-0.53

znac

-0.53

Demikian

-0.52

 怎样

-0.52

новниш

-0.51

 fallu

-0.51

CWE

-0.51

 unknownFields

-0.50

POSITIVE LOGITS

 الرخصة

0.55

UpInside

0.53

 Approach

0.50

 IndexPath

0.49

 }}"></

0.47

֑

0.47

DoubleQuotes

0.47

ocin

0.47

PYX

0.46

 tracks

0.45

Activations Density 1.114%

technical language and formatting related to mathematical notation

No Comments

No Known Activations