INDEX

Explanations

symbols and notations typically used in mathematical expressions or equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

LookAnd

-0.94

GEBURTSDATUM

-0.93

webElementXpaths

-0.92

AnchorStyles

-0.89

webElement

-0.87

InvalidProtocol

-0.86

SharedCtor

-0.82

 للاسماء

-0.82

 BIBSYS

-0.81

 EconPapers

-0.79

POSITIVE LOGITS

nsf

0.48

</em>

0.46

</strong>

0.44

”

0.44

<strong>

0.43

0.40

<em>

0.39

 olev

0.39

下

0.38

Activations Density 0.570%

symbols and notations typically used in mathematical expressions or equations

No Comments

No Known Activations