INDEX

Explanations

mathematical expressions and concepts related to positive values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 kasarigan

-1.42

InjectAttribute

-1.24

Geplaatst

-1.24

ItemBackground

-1.19

 betweenstory

-1.17

 ―――――

-1.11

 المعيارى

-1.11

parsedMessage

-1.09

 itſelf

-1.09

ViewFeatures

-1.08

POSITIVE LOGITS

0.67

0.59

0.57

0.54

ne

0.53

0.52

Activations Density 1.057%

mathematical expressions and concepts related to positive values

No Comments

No Known Activations