INDEX

Explanations

references to specific names, particularly of people and places, in relation to events or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

__':

-0.89

 onOptions

-0.85

__':

-0.74

Captor

-0.73

{#

-0.71

ScopeManager

-0.68

++);

-0.68

DataAnnotations

-0.67

ArgumentParser

-0.66

__":

-0.66

POSITIVE LOGITS

 omicron

0.66

Covid

0.63

 pandémie

0.62

 covid

0.62

 pandemic

0.61

 Covid

0.61

 COVID

0.61

 Omicron

0.60

 intérieure

0.60

COVID

0.58

Activations Density 0.113%

references to specific names, particularly of people and places, in relation to events or actions

No Comments

No Known Activations