INDEX

Explanations

mathematical symbols and formatting in equations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

GenerationType

-0.96

 estimés

-0.87

 للمعارف

-0.86

ality

-0.85

Lorenzo

-0.85

Mathias

-0.85

 Whirlpool

-0.83

LOY

-0.82

 Lorenzo

-0.81

VES

-0.79

POSITIVE LOGITS

={`/

0.91

 numberWith

0.89

 Reif

0.84

ymce

0.78

schul

0.77

setVerticalGroup

0.76

THOR

0.73

âmara

0.72

ednesdays

0.72

 erfre

0.72

Activations Density 1.770%

mathematical symbols and formatting in equations

No Comments

No Known Activations