INDEX

Explanations

occurrences of print statements in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 bArr

-0.64

FormTagHelper

-0.59

 himo

-0.59

 صوتيه

-0.58

"*.

-0.56

 Nusa

-0.55

Morse

-0.54

][$

-0.54

 Morse

-0.53

=?";

-0.53

POSITIVE LOGITS

WriteLine

1.03

println

1.01

Println

0.98

נטרנט

0.89

WithFormat

0.83

writerow

0.82

<tr>

0.81

print

0.79

 calendriers

0.79

ंदीखरीदारी

0.77

Activations Density 0.018%

occurrences of print statements in the text

No Comments

No Known Activations