INDEX

Explanations

specific brand or product names in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 nahilalakip

-0.71

TypedDataSet

-0.70

ValueStyle

-0.70

 typelib

-0.69

 ویکی‌پدیای

-0.68

 inoxidable

-0.66

Бахар

-0.65

AccessorTable

-0.64

etheless

-0.63

hyrchwyd

-0.63

POSITIVE LOGITS

™

0.41

glVertex

0.41

 series

0.40

 enda

0.40

Privat

0.40

Advantage

0.39

BeginInit

0.39

füllen

0.39

 impressão

0.39

Lutz

0.39

Activations Density 0.444%

specific brand or product names in various contexts

No Comments

No Known Activations