INDEX

Explanations

technical terms and specific details related to programming or software attributes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GING

-0.50

BeginContext

-0.45

CopyWith

-0.42

serviceWorker

-0.42

ạc

-0.41

sda

-0.41

Gef

-0.40

aip

-0.40

 quitte

-0.40

AddRange

-0.39

POSITIVE LOGITS

mybatisplus

1.01

GEBURTSDATUM

0.99

 صوتيه

0.91

 ComVisible

0.81

󠁴

0.81

 AssemblyVersion

0.79

UnsafeEnabled

0.76

 henvisninger

0.71

 nakalista

0.71

енча

0.70

Activations Density 1.059%

technical terms and specific details related to programming or software attributes

No Comments

No Known Activations