INDEX

Explanations

phrases indicating assertions or confirmations of expectations and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

لينكات

-0.58

 ActionResult

-0.56

IActionResult

-0.54

 Philo

-0.54

msgSender

-0.52

WPS

-0.50

<%@

-0.49

 IActionResult

-0.48

mipmap

-0.47

onAttach

-0.47

POSITIVE LOGITS

 ویکی‌پدیا

0.74

 ویکی‌پدی

0.71

amaño

0.65

setof

0.63

 propOrder

0.61

Tetapi

0.58

 utafitiHapana

0.56

íny

0.56

Jereo

0.55

verwijspagina

0.55

Activations Density 1.547%

phrases indicating assertions or confirmations of expectations and outcomes

No Comments

No Known Activations