INDEX

Explanations

punctuation marks and formatting elements in the text

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

Word after a newline character or sentence start

np_acts-logits-general · gemini-2.0-flash

proper nouns and names

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

 entanto

-0.74

новништво

-0.74

-};

-0.72

Revenir

-0.72

tvguidetime

-0.69

)}</

-0.68

люс

-0.68

ępnie

-0.68

gdx

-0.68

TemporalType

-0.67

POSITIVE LOGITS

When

0.93

Sometimes

0.89

 When

0.81

 Sometimes

0.79

Since

0.77

 Often

0.73

Often

0.73

There

0.73

Every

0.72

Everyone

0.72

Activations Density 0.258%

punctuation marks and formatting elements in the text

Word after a newline character or sentence start

proper nouns and names

No Comments

No Known Activations