INDEX

Explanations

references to system-related terms or commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

aarrggbb

-0.68

 onData

-0.67

 InputDecoration

-0.63

/******/

-0.56

errHandler

-0.55

 defaultstate

-0.53

 onAnimation

-0.53

้อมูล

-0.52

BagLayout

-0.51

Literatur

-0.50

POSITIVE LOGITS

system

0.74

 systemic

0.67

 Mous

0.64

 Systemic

0.60

}")]

0.58

 Greeley

0.58

 TextAppearance

0.57

 Courant

0.56

 resourceCulture

0.56

เจ้า

0.55

Activations Density 0.167%

references to system-related terms or commands

No Comments

No Known Activations