INDEX

Explanations

mentions of a specific identifier related to a "PD" (possibly referring to a project descriptor or protocol)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

DeleteBehavior

-0.65

Bibliograf

-0.63

 mouseClicked

-0.63

ImageContext

-0.62

IsContent

-0.61

UnsafeEnabled

-0.61

unders

-0.61

epy

-0.61

 enumeration

-0.59

 ?></

-0.59

POSITIVE LOGITS

 fame

0.75

ld

0.65

 parliament

0.63

 nozze

0.60

 Parliament

0.57

fame

0.57

Id

0.54

lusconi

0.54

Javadoc

0.53

HS

0.52

Activations Density 0.111%

mentions of a specific identifier related to a "PD" (possibly referring to a project descriptor or protocol)

No Comments

No Known Activations