INDEX

Explanations

components related to features, specifications, and instructions for products or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Tikang

-0.67

ArgsConstructor

-0.66

 المعيارى

-0.63

 estoppel

-0.62

ItemBackground

-0.62

 Attractions

-0.61

 Salts

-0.60

 rospy

-0.59

ాన

-0.59

 Plast

-0.58

POSITIVE LOGITS

The

0.73

And

0.70

そして

0.61

diğinde

0.60

&=&\

0.60

öhnt

0.60

hdashline

0.59

);?>

0.58



0.58

getOr

0.58

Activations Density 0.183%

components related to features, specifications, and instructions for products or systems

No Comments

No Known Activations