INDEX

Explanations

phrases that indicate quantities or relationships between items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 purpoſe

-0.93

 houſe

-0.85

 pleaſure

-0.84

 Houſe

-0.83

Eſ

-0.79

 greateſt

-0.79

 ſtate

-0.77

 uſe

-0.75

Efq

-0.72

 faſt

-0.72

POSITIVE LOGITS

 three

0.70

six

0.67

verwijspagina

0.66

 four

0.65

two

0.62

 these

0.61

MigrationBuilder

0.60

 disambiguazione

0.60

 toilettes

0.60

of

0.59

Activations Density 0.117%

phrases that indicate quantities or relationships between items

No Comments

No Known Activations