INDEX

Explanations

lines of documentation or comments within code snippets

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

Code delimiters: quotation marks and apostrophes

np_acts-logits-general · gemini-2.0-flash

docstring delimiters

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

fromnode

-1.01

ſammen

-0.91

ロウィン

-0.91

iſche

-0.91

bootstrapcdn

-0.89

الإنجليزية

-0.89

iſchen

-0.88

<unused28>

-0.88

<unused16>

-0.88

<unused8>

-0.88

POSITIVE LOGITS

"""

1.17

"""

0.73

"""

0.72

."""

0.60

""""

0.56

("""

0.54

'''

0.52

0.50

“

0.50

0.45

Activations Density 0.062%

lines of documentation or comments within code snippets

Code delimiters: quotation marks and apostrophes

docstring delimiters

No Comments

No Known Activations