INDEX

Explanations

references to historical figures or events, particularly in the context of Hollywood

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

Follows possessive nouns

np_acts-logits-general · gemini-2.0-flash

people's names and family relationships

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

-0.56

”

-0.56

‘

-0.52

he

-0.52

“

-0.51

who

-0.51

we

-0.49

is

-0.49

POSITIVE LOGITS

GEBURTSDATUM

0.88

 समीक्षक

0.75

 jsPsych

0.72

 يتيمه

0.70

 Anſ

0.69

 Diſ

0.65

 houſe

0.64

 Houſe

0.62

 Reſ

0.62

 Hernando

0.61

Activations Density 0.333%

references to historical figures or events, particularly in the context of Hollywood

Follows possessive nouns

people's names and family relationships

No Comments

No Known Activations