INDEX

Explanations

occurrences of the word "click" and its variations in the context of user interactions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Normdatei

-0.55

Leopold

-0.45

(&:

-0.44

NewUrlParser

-0.43

CppMethod

-0.42

 ujednoznacz

-0.42

 Leopold

-0.40

Enjoy

-0.39

 الحره

-0.39

/^[

-0.39

POSITIVE LOGITS

 clicking

0.69

 defaultstate

0.66

 clicked

0.66

click

0.65

 click

0.65

clicking

0.59

Click

0.56

Pressed

0.56

 clicks

0.56

CLICK

0.54

Activations Density 1.667%

occurrences of the word "click" and its variations in the context of user interactions

No Known Activations