INDEX

Explanations

occurrences of the term "any."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

lüğ

-0.76

 Calabria

-0.71

 Plutarch

-0.70

 Cataluña

-0.68

 Thun

-0.67

lıyor

-0.65

Griffin

-0.65

 kine

-0.64

zeka

-0.64

 Když

-0.63

POSITIVE LOGITS

any

1.86

Any

1.72

ANY

1.60

Any

1.58

any

1.40

ANY

1.24

 qualsiasi

1.07

任何

1.07

 other

1.06

 cualquier

1.04

Activations Density 0.127%

occurrences of the term "any."

No Comments

No Known Activations