INDEX

Explanations

instances of unique identifiers or markers in a dataset

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

Appears after math operators or symbols

np_acts-logits-general · gemini-2.0-flash

mathematicsbiologycomputer science

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-1.28

-1.25

-1.18

-1.09

-1.02

“

-0.97

in

-0.95

-0.94

POSITIVE LOGITS

 itſelf

1.59

 ་་

1.53

 pleaſure

1.48

 ſind

1.40

 houſe

1.40

 purpoſe

1.40

 ſtate

1.39

 Houſe

1.38

 doubtnut

1.35

 vectorstock

1.33

Activations Density 7.718%

instances of unique identifiers or markers in a dataset

Appears after math operators or symbols

mathematicsbiologycomputer science

No Comments

No Known Activations