INDEX

Explanations

punctuation marks and symbols used for text markup or formatting

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

Code snippets and math formulas

np_acts-logits-general · gemini-2.0-flash

choice you know

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

-0.53

 again

-0.46

 even

-0.46

-0.45

-0.43

and

-0.40

-0.39

and

-0.39

—

-0.39

POSITIVE LOGITS

MigrationBuilder

1.31

Geplaatst

1.08

BeginContext

1.06

 &___

1.00

Personendaten

1.00

SourceChecksum

0.98

<bos>

0.94

الإنجليزية

0.93

bootstrapcdn

0.93

 تضيفلها

0.92

Activations Density 0.576%

punctuation marks and symbols used for text markup or formatting

Code snippets and math formulas

choice you know

No Comments

No Known Activations