INDEX

Explanations

mathematical expressions and terms related to proofs and estimations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 يتيمه

-0.66

StructEnd

-0.63

protoimpl

-0.61

 lids

-0.59

 Wikidata

-0.56

 dâu

-0.56

uckleberry

-0.56

rangea

-0.55

subpackage

-0.53

 wechsel

-0.53

POSITIVE LOGITS

 AssemblyCulture

0.62

webElementGuid

0.54

//</

0.54

گذ

0.51

Xo

0.50

 Default

0.50

lorette

0.49

"><?

0.48

AEL

0.48

بوك

0.47

Activations Density 0.791%

mathematical expressions and terms related to proofs and estimations

No Comments

No Known Activations