INDEX

Explanations

warnings or prohibitive language in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

"):

-0.77

__":

-0.74

itemBuilder

-0.74

WebServlet

-0.72

"],

-0.71

"),

-0.71

"){

-0.70

")){

-0.69

"""

-0.69

zarchiwizowane

-0.68

POSITIVE LOGITS

0.76

!!!

0.65

!!

0.60

!!!!

0.57

!.

0.57

0.56

ー

0.55

Билгалдахарш

0.55

 poveznice

0.54

!!!!!

0.53

Activations Density 0.895%

warnings or prohibitive language in text

No Comments

No Known Activations