INDEX

Explanations

historical references to titles, positions, and territorial governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

umumkan

-0.45

merking

-0.41

betic

-0.41

astify

-0.40

#+#

-0.40

]}>

-0.40

>({

-0.39

OID

-0.38

❖

-0.38

-------------</

-0.38

POSITIVE LOGITS

 blanches

0.66

findpost

0.62

UpInside

0.62

الدراسه

0.62

 bumbu

0.60

æus

0.60

webElementXpaths

0.59

 Brescia

0.59

EditorBrowsable

0.59

وافق

0.58

Activations Density 8.032%

historical references to titles, positions, and territorial governance

No Comments

No Known Activations