INDEX

Explanations

instances of the word "new"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 indígen

-0.78

 للاسماء

-0.75

 pleaſure

-0.70

 increí

-0.68

 circulación

-0.67

iNdEx

-0.65

 kapture

-0.64

 avoient

-0.63

IActionResult

-0.63

uestamente

-0.63

POSITIVE LOGITS

new

1.26

new

1.04

New

0.77

0.73

NEW

0.68

an

0.66

 새로운

0.65

NEW

0.63

New

0.63

 small

0.62

Activations Density 0.050%

instances of the word "new"

No Comments

No Known Activations

instances of the word "new"

No Comments

No Known Activations