INDEX

Explanations

mentions of the term "broad" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

AccessFile

-0.95

engin

-0.86

ंदीखरीदारी

-0.86

 petitioners

-0.85

 installers

-0.83

Utf

-0.82

 Merz

-0.79

 AttributeSet

-0.77

()?;

-0.77

 Apri

-0.77

POSITIVE LOGITS

 Broad

1.10

Broad

1.01

broad

0.94

 broad

0.92

ness

0.87

Portail

0.83

 broadly

0.81

 BROAD

0.78

 broader

0.77

 Brod

0.71

Activations Density 0.115%

mentions of the term "broad" and its variations in various contexts

No Comments

No Known Activations