INDEX

Explanations

negative symbols or indicators

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

Code and text between quotation marks

np_acts-logits-general · gemini-2.0-flash

technical programming and syntax

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ed

-1.03

-1.02

ه

-0.80

ي

-0.77

onde

-0.73

нке

-0.73

ה

-0.71

-0.69

 tank

-0.69

ORE

-0.68

POSITIVE LOGITS

__':

1.31

']))

1.30

]))

1.30

()))

1.29

}")

1.24

'))

1.23

__":

1.22

))

1.22

}));

1.19

)))

1.18

Activations Density 0.061%

negative symbols or indicators

Code and text between quotation marks

technical programming and syntax

No Comments

No Known Activations