INDEX

Explanations

code that defines the main execution entry point in a script

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

code structure syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ſelf

-0.65

lgari

-0.62

Saxon

-0.60

 StringVar

-0.60

 pleaſure

-0.59

 vectorstock

-0.58

ittarius

-0.57

 SqlDbType

-0.57

medriver

-0.57

usermodel

-0.56

POSITIVE LOGITS

__':

2.59

__":

2.38

__':

2.08

__":

1.89

})));

0.55

setVerticalGroup

0.52

])):

0.51

:}

0.49

MemoryWarning

0.48

Activations Density 0.000%

code that defines the main execution entry point in a script

code structure syntax

No Comments

No Known Activations