INDEX

Explanations

proper nouns and specific titles within the text

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

 ویکی‌پدیا

-0.58

PreAuthorize

-0.56

Kanpo

-0.55

Datuak

-0.53

didSet

-0.51

ImageContext

-0.51

WithMany

-0.51

 espada

-0.50

 paio

-0.50

 dénon

-0.50

POSITIVE LOGITS

 للمعارف

0.75

AccessorTable

0.66

 referenties

0.65

rizona

0.54

orale

0.54

 proceeds

0.53

oidal

0.53

 unique

0.52

дата

0.51

이는

0.51

Activations Density 0.506%

proper nouns and specific titles within the text

No Comments

No Known Activations