INDEX

Explanations

instances of the word "take" and its variations, indicating a focus on the concept of taking action or undergoing experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

feitura

-0.70

 TestBed

-0.68

jspx

-0.67

 &___

-0.66

Hochspringen

-0.64

 GreatSchools

-0.62

tvguidetime

-0.62

ResumeLayout

-0.62

 متعلقه

-0.61

 mapStateToProps

-0.59

POSITIVE LOGITS

 place

0.60

تقاوى

0.56

Takes

0.50

Place

0.49

us

0.48

 виправивши

0.47

 exactly

0.47

place

0.46

tagHelperRunner

0.45

takes

0.45

Activations Density 0.073%

instances of the word "take" and its variations, indicating a focus on the concept of taking action or undergoing experiences

No Comments

No Known Activations