INDEX

Explanations

patterns related to file formatting or metadata in textual content

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

 Audiodateien

-0.80

 فريبيس

-0.76

^(@)

-0.71

GHIJKLM

-0.69

ReusableCell

-0.64

ForResult

-0.64



-0.61

 estekak

-0.59

Дереккөздер

-0.58

EndContext

-0.58

POSITIVE LOGITS

@"/

0.59

via

0.52

 Venezia

0.50

 loup

0.49

áklad

0.47

 Kamil

0.47

 overflows

0.47

 επικ

0.47

 Garibaldi

0.46

liferay

0.46

Activations Density 0.364%

patterns related to file formatting or metadata in textual content

No Comments

No Known Activations