INDEX

Explanations

occurrences of the word "google" and employment-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

JspWriter

-0.73

 mergeFrom

-0.68

wapV

-0.66

jface

-0.63

 Altman

-0.61

 Wolfe

-0.60

FormState

-0.59

которые

-0.58

 vagyok

-0.58

stylers

-0.58

POSITIVE LOGITS

 lend

1.31

 borrow

1.07

 lending

1.00

 lends

0.95

 Borrow

0.93

Borrow

0.92

 Lending

0.91

 BORROW

0.89

 borrowed

0.88

 Lend

0.87

Activations Density 0.056%

occurrences of the word "google" and employment-related terms

No Comments

No Known Activations