INDEX

Explanations

references to incidents involving protests and law enforcement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 AssemblyCulture

-0.54

الحياه

-0.45

uhi

-0.41

DOCTYPE

-0.41

erecht

-0.41

 Waray

-0.41

PropertyChanging

-0.40

elson

-0.40

POD

-0.40

ваш

-0.40

POSITIVE LOGITS

UnusedPrivate

0.91

 Meksiku

0.74

CloseOperation

0.66

canestro

0.58

المناصب

0.57

Rhestr

0.57

 кӀ

0.57

 uintptr

0.57

 masturb

0.55

MultipartFile

0.55

Activations Density 0.399%

references to incidents involving protests and law enforcement

No Comments

No Known Activations