INDEX

Explanations

terms related to "name" and "identifier."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 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

reportWebVitals

-0.48

 Cyclo

-0.43

pul

-0.43

InjectAttribute

-0.42

 JSTOR

-0.42

Oli

-0.41

Dij

-0.41

ابراین

-0.41

躇

-0.41

cru

-0.40

POSITIVE LOGITS

 name

2.89

 Name

2.73

 names

2.69

 NAME

2.58

Name

2.50

 Names

2.48

 Namen

2.44

NAME

2.31

name

2.22

 nome

2.17

Activations Density 0.202%

terms related to "name" and "identifier."

No Comments

No Known Activations

terms related to "name" and "identifier."

No Comments

No Known Activations