INDEX

Explanations

details about concealment and secretive actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

<bos>

-0.62

şiv

-0.47

XMLSchema

-0.45

BASEPATH

-0.44

Yea

-0.44

 considérons

-0.44

JScrollPane

-0.40

 psycopg

-0.39

Tip

-0.39

-0.38

POSITIVE LOGITS

 مرئيه

0.93

">//

0.82

NUMX

0.77

kuuta

0.71

$_"

0.70

новниш

0.69

}{*}{}

0.69

 تانيه

0.69

WriteBarrier

0.68

Efq

0.68

Activations Density 0.116%

details about concealment and secretive actions

No Comments

No Known Activations