INDEX

Explanations

mathematical notation and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

AP

-0.41

user

-0.34

Color

-0.33

set

-0.32

NE

-0.32

mo

-0.32

POSITIVE LOGITS

parsedMessage

0.79

󠁢

0.75

 disambiguazione

0.74



0.74

httphttps

0.74

RetentionPolicy

0.73

reportWebVitals

0.73

 snippetHide

0.73

TemporalType

0.72

rungsseite

0.72

Activations Density 0.200%

mathematical notation and symbols

No Comments

No Known Activations