INDEX

Explanations

unique symbols or characters that indicate specific formatting or notational elements in mathematical and scientific contexts

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

Followed by a punctuation mark or math symbol

np_acts-logits-general · gemini-2.0-flash

V or N followed by punctuation

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

<eos>

-1.02

-0.78

-0.73

-0.66

</em>

-0.65

—

-0.61

</i>

-0.60

 also

-0.58

↵

-0.57

POSITIVE LOGITS

 ujednoznacz

1.18

 myſelf

1.05

StoryboardSegue

1.01

AsUp

0.98

utilisons

0.97

PerformLayout

0.95

IntoConstraints

0.95

 Roskov

0.95

 disambiguazione

0.95

 tartalomajánló

0.94

Activations Density 0.447%

unique symbols or characters that indicate specific formatting or notational elements in mathematical and scientific contexts

Followed by a punctuation mark or math symbol

V or N followed by punctuation

No Comments

No Known Activations

unique symbols or characters that indicate specific formatting or notational elements in mathematical and scientific contexts

Followed by a punctuation mark or math symbol

V or N followed by punctuation

No Comments

No Known Activations